{"paper_id": "3d2b956498bd9c38ea278c7ed789e87b332bf295", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nInterpretation Seroprevalence of MERS-CoV antibodies was signifi cantly higher in camel-exposed individuals than in the general population . By simple multiplication , a projected 44 951 ( 95 % CI 26 971-71 922 ) individuals older than 15 years might be seropositive for MERS-CoV in Saudi Arabia . These individuals might be the source of infection for patients with confi rmed MERS who had no previous exposure to camels .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Interpretation Seroprevalence of MERS-CoV antibodies was signifi cantly higher in camel-exposed individuals than in the general population .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 1}, {\"segment_text\": \"By simple multiplication , a projected 44 951 ( 95 % CI 26 971-71 922 ) individuals older than 15 years might be seropositive for MERS-CoV in Saudi Arabia .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 2}, {\"segment_text\": \"These individuals might be the source of infection for patients with confi rmed MERS who had no previous exposure to camels .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}]}"}]}
{"paper_id": "cc03e915afeb7acfe93595b75a38f7b58bf2d752", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground and Aim : Avian coronavirus has a wide range of hosts , from chickens and turkeys to wild birds . This virus causes an economically and , possibly , environmentally , important loss in the poultry industry . Therefore , research into the avian coronavirus in various species of birds is required . The Eclectus parrot ( Eclectus roratus ) is an endemic bird to Indonesia and Northern Australia and often kept as pets . At present , there has been limited information about avian coronavirus infection among birds . This study aimed to determine the presence of and to characterize avian coronavirus isolated from Eclectus parrots in Indonesia . Cloacal swab samples were taken from 10 healthy Eclectus parrots ( E. roratus ) . Each isolate was propagated into specific pathogen-free embryonated chicken eggs . The presence of avian coronavirus was determined using three sets of primers targeting the 3 ' untranslated region ( 3 ' - UTR ) of avian coronavirus ( UTR41 + / 11 − ) , the N gene of the infectious bronchitis virus ( IBVN + / − ) , and the S1 gene of the IBV ( XCE2 + / XCE2 − ) . The infectious bronchitis vaccine strain H120 was used as a positive control . Resulting positive bands were sequenced for the S1 gene . Results : None of the isolates was positive for the 3 ' - UTR , four isolates were positive for the N gene of infectious bronchitis , and two isolates were positive for the S1 gene of the IBV . However , only one isolate ( parrot/Indonesia/BX9 / 16 ) was sequenced for the partial S1 gene with primers XCE2 + / XCE2 − . The partial nucleotide sequence of this isolate showed 100 % homology with the IBV GI-13 lineage , specifically with a field isolate of the 4/91 variant 1 Israel and the 4/91 vaccine on the hypervariable region 3 site of the S1 gene . An IB-like avian coronavirus was isolated from healthy Eclectus parrots . Our results indicate that IBV has a wide range of hosts , which prompt the need to understand the interspecies connection of this virus better .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background and Aim : Avian coronavirus has a wide range of hosts ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"from chickens and turkeys to wild birds .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"This virus causes an economically and ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"possibly , environmentally , important loss in the poultry industry .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Therefore , research into the avian coronavirus in various species of birds is required .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"The Eclectus parrot ( Eclectus roratus ) is an endemic bird to Indonesia and Northern Australia and often kept as pets .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"At present , there has been limited information about avian coronavirus infection among birds .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"This study aimed to determine the presence of and to characterize avian coronavirus isolated from Eclectus parrots in Indonesia .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"Cloacal swab samples were taken from 10 healthy Eclectus parrots ( E. roratus ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Each isolate was propagated into specific pathogen-free embryonated chicken eggs .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"The presence of avian coronavirus was determined using three sets of primers targeting the 3 ' untranslated region ( 3 ' - UTR ) of avian coronavirus ( UTR41 + / 11 − ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"the N gene of the infectious bronchitis virus ( IBVN + / − ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"and the S1 gene of the IBV ( XCE2 + / XCE2 − ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"The infectious bronchitis vaccine strain H120 was used as a positive control .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"Resulting positive bands were sequenced for the S1 gene .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 15}, {\"segment_text\": \"Results : None of the isolates was positive for the 3 ' - UTR ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"four isolates were positive for the N gene of infectious bronchitis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"and two isolates were positive for the S1 gene of the IBV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"However , only one isolate ( parrot/Indonesia/BX9 / 16 ) was sequenced for the partial S1 gene with primers XCE2 + / XCE2 − .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"The partial nucleotide sequence of this isolate showed 100 % homology with the IBV GI-13 lineage ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"specifically with a field isolate of the 4/91 variant 1 Israel and the 4/91 vaccine on the hypervariable region 3 site of the S1 gene .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"An IB-like avian coronavirus was isolated from healthy Eclectus parrots .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"Our results indicate that IBV has a wide range of hosts ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"which prompt the need to understand the interspecies connection of this virus better .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}]}"}]}
{"paper_id": "c1eb7483446895edd38acb64e683bfd905d54211", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nHigh consequence human pathogenic viruses must be handled at biosafety level 2 , 3 or 4 and must be rendered non-infectious before they can be utilized for molecular or immunological applications at lower biosafety levels . Here we evaluate psoralen-inactivated Arena - , Bunya - , Corona - , Filo - , Flavi-and Orthomyxoviruses for their suitability as antigen in immunological processes and as template for reverse transcription PCR and sequencing . The method of virus inactivation using a psoralen molecule appears to have broad applicability to RNA viruses and to leave both the particle and RNA of the treated virus intact , while rendering the virus non-infectious .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"High consequence human pathogenic viruses must be handled at biosafety level 2 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"3 or 4 and must be rendered non-infectious before they can be utilized for molecular or immunological applications at lower biosafety levels .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Here we evaluate psoralen-inactivated Arena - ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"Bunya - , Corona - ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Filo - , Flavi-and Orthomyxoviruses for their suitability as antigen in immunological processes and as template for reverse transcription PCR and sequencing .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"The method of virus inactivation using a psoralen molecule appears to have broad applicability to RNA viruses and to leave both the particle and RNA of the treated virus intact ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"while rendering the virus non-infectious .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}]}"}]}
{"paper_id": "4af50c8534fa874447eb227dc762eb3f9503e62f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nChemical compounds studied in this article : Formaldehyde ( PubChem CID : 712 ) Ethanol ( PubChem CID : 702 ) Dexamethasone ( PubChem CID : 5743 ) Polymyxin B ( PubChem CID : 49800004 ) . Ethnopharmacological relevance : Houttuynia cordata ( HC ) has been used as a folk therapy to treat pulmonary infections . This study aimed to determine the role and mechanism of action of polysaccharides isolated from HC ( HCP ) in lipopolysaccharide ( LPS ) - induced ALI in the mice . Materials and methods : LPS was delivered by the intratracheal route to Balb/c mice 2 h before HCP ( 40 , 80 and 160 mg/kg ) administration . Results : The number of total cells , protein and tumor necrosis factor-α ( TNF-α ) concentrations in bronchoalveolar lavage fluid , the wet/dry weight ratio ( w/d ) of lungs and pulmonary pathology of each mouse were analyzed , it was found that HCP significantly alleviated ALI induced by LPS . Moreover , in lungs of mice , it was found that the infiltration of inflammatory cells , the expression of Toll-like receptor 4 and complement deposition were significantly decreased by HCP treatment . In vitro assays showed that C5a , a complement activation product , induced significant macrophage migration and treatment with HCP prevented it . The in vitro results also proved that LPS increased nitric oxide and pro-inflammatory cytokines ( TNF-α , interleukin-6 , and interleukin-1β ) production , and HCP antagonized these effects of LPS . It was also found that HCP alone augmented secretion of some pro-inflammatory cytokines . Conclusion : These results indicate that HCP may alleviate LPS induced lung inflammatory injury , which may be associated with its inhibitory effect on the over activation of complement and macrophages . This suggests a potential role to treat ALI .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Chemical compounds studied in this article : Formaldehyde ( PubChem CID : 712 ) Ethanol ( PubChem CID : 702 ) Dexamethasone ( PubChem CID : 5743 ) Polymyxin B ( PubChem CID : 49800004 ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Ethnopharmacological relevance : Houttuynia cordata ( HC ) has been used as a folk therapy to treat pulmonary infections .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"This study aimed to determine the role and mechanism of action of polysaccharides isolated from HC ( HCP ) in lipopolysaccharide ( LPS ) - induced ALI in the mice .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"Materials and methods : LPS was delivered by the intratracheal route to Balb/c mice 2 h before HCP ( 40 , 80 and 160 mg/kg ) administration .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Results : The number of total cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"protein and tumor necrosis factor-α ( TNF-α ) concentrations in bronchoalveolar lavage fluid ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"the wet/dry weight ratio ( w/d ) of lungs and pulmonary pathology of each mouse were analyzed ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"it was found that HCP significantly alleviated ALI induced by LPS .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Moreover , in lungs of mice ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"it was found that the infiltration of inflammatory cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"the expression of Toll-like receptor 4 and complement deposition were significantly decreased by HCP treatment .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"In vitro assays showed that C5a ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"a complement activation product , induced significant macrophage migration and treatment with HCP prevented it .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"The in vitro results also proved that LPS increased nitric oxide and pro-inflammatory cytokines ( TNF-α , interleukin-6 , and interleukin-1β ) production ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"and HCP antagonized these effects of LPS .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"It was also found that HCP alone augmented secretion of some pro-inflammatory cytokines .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Conclusion : These results indicate that HCP may alleviate LPS induced lung inflammatory injury ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"which may be associated with its inhibitory effect on the over activation of complement and macrophages .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"This suggests a potential role to treat ALI .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}]}"}]}
{"paper_id": "a34d2c1876ffedc4f95f3af13ac06039cd38a5b0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAdjusting for delay from confirmation-to-death , we estimated case and infection fatality ratios ( CFR , IFR ) for COVID-19 on the Diamond Princess ship as 2.3 % ( 0.75 % -5.3 % ) and 1.2 % ( 0.38-2.7 % ) . Comparing deaths onboard with expected deaths based on naive CFR estimates using China data , we estimate IFR and CFR in China to be 0.5 % ( 95 % CI : 0.2-1.2 % ) and 1.1 % ( 95 % CI : 0.3-2.4 % ) respectively .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Adjusting for delay from confirmation-to-death ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"we estimated case and infection fatality ratios ( CFR , IFR ) for COVID-19 on the Diamond Princess ship as 2.3 % ( 0.75 % -5.3 % ) and 1.2 % ( 0.38-2.7 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"Comparing deaths onboard with expected deaths based on naive CFR estimates using China data ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 3}, {\"segment_text\": \"we estimate IFR and CFR in China to be 0.5 % ( 95 % CI : 0.2-1.2 % ) and 1.1 % ( 95 % CI : 0.3-2.4 % ) respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}]}"}]}
{"paper_id": "2769723b9b497b45c8178f8f68dc48a5fed06db6", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBagaza virus is a mosquito-borne flavivirus , first isolated in 1966 in Central African Republic . It has currently been identified in mosquito pools collected in the field in West and Central Africa . Emergence in wild birds in Europe and serological evidence in encephalitis patients in India raise questions on its genetic evolution and the diversity of isolates circulating in Africa . To better understand genetic diversity and evolution of Bagaza virus , we describe the full-genome characterization of 11 West African isolates , sampled from 1988 to 2014 . Parameters such as genetic distances , N-glycosylation patterns , recombination events , selective pressures , and its codon adaptation to human genes are assessed . Our study is noteworthy for the observation of N-glycosylation and recombination in Bagaza virus and provides insight into its Indian origin from the 13th century . Interestingly , evidence of Bagaza virus codon adaptation to human house-keeping genes is also observed to be higher than those of other flaviviruses well known in human infections . Genetic variations on genome of West African Bagaza virus could play an important role in generating diversity and may promote Bagaza virus adaptation to other vertebrates and become an important threat in human health . 2 of 26 meningoencephalitis virus ( ITV ) , a pathogen affecting poultry ( turkeys ) and close to West Nile virus ( WNV ) in several genomic regions ( 3 , 11 ) . Although diverse studies have contributed greatly to our understanding of the transmission modes of BAGV ( 8 , 12 ) and the pathogenesis of BAGV infection ( 13 ) , only one study has addressed BAGV genetic diversity , reporting a high homology > 90 % between Central African Republic , Indian and Spanish BAGV isolates ( 9 ) . In West Africa , there is a lack of data on BAGV genetic diversity . To fill this gap and gain better insights into BAGV molecular evolution , we characterized the full-genome of 11 BAGV isolates , sampled from 1988 to 2014 in Senegal and Côte d'Ivoire . Firstly , we assessed genetic distances , phylogenetically informative sites found in more than one sequence contributing to branch ordering , N-glycosylation patterns , recombination events , selective pressures on West African BAGV sequences and their evolutionary phylogenetic relationships with previously available BAGV genomes . Secondly , to assess evidence of future BAGV codon adaptation to human house-keeping genes , a bio-informatics approach was used for analysis of codon adaptation biases .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Bagaza virus is a mosquito-borne flavivirus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"first isolated in 1966 in Central African Republic .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"It has currently been identified in mosquito pools collected in the field in West and Central Africa .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Emergence in wild birds in Europe and serological evidence in encephalitis patients in India raise questions on its genetic evolution and the diversity of isolates circulating in Africa .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"To better understand genetic diversity and evolution of Bagaza virus ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"we describe the full-genome characterization of 11 West African isolates ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"sampled from 1988 to 2014 .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"Parameters such as genetic distances ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"N-glycosylation patterns , recombination events ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"selective pressures , and its codon adaptation to human genes are assessed .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Our study is noteworthy for the observation of N-glycosylation and recombination in Bagaza virus and provides insight into its Indian origin from the 13th century .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Interestingly , evidence of Bagaza virus codon adaptation to human house-keeping genes is also observed to be higher than those of other flaviviruses well known in human infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Genetic variations on genome of West African Bagaza virus could play an important role in generating diversity and may promote Bagaza virus adaptation to other vertebrates and become an important threat in human health .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"2 of 26 meningoencephalitis virus ( ITV ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"a pathogen affecting poultry ( turkeys ) and close to West Nile virus ( WNV ) in several genomic regions ( 3 , 11 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Although diverse studies have contributed greatly to our understanding of the transmission modes of BAGV ( 8 , 12 ) and the pathogenesis of BAGV infection ( 13 ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 16}, {\"segment_text\": \"only one study has addressed BAGV genetic diversity ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 17}, {\"segment_text\": \"reporting a high homology > 90 % between Central African Republic ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Indian and Spanish BAGV isolates ( 9 ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 19}, {\"segment_text\": \"In West Africa , there is a lack of data on BAGV genetic diversity .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 20}, {\"segment_text\": \"To fill this gap and gain better insights into BAGV molecular evolution ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"we characterized the full-genome of 11 BAGV isolates ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"sampled from 1988 to 2014 in Senegal and Côte d'Ivoire .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"Firstly , we assessed genetic distances ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 24}, {\"segment_text\": \"phylogenetically informative sites found in more than one sequence contributing to branch ordering ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 25}, {\"segment_text\": \"N-glycosylation patterns , recombination events ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 26}, {\"segment_text\": \"selective pressures on West African BAGV sequences and their evolutionary phylogenetic relationships with previously available BAGV genomes .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 27}, {\"segment_text\": \"Secondly , to assess evidence of future BAGV codon adaptation to human house-keeping genes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 28}, {\"segment_text\": \"a bio-informatics approach was used for analysis of codon adaptation biases .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 29}]}"}]}
{"paper_id": "e67eb3bd9090630fa37b601957ed1dcc088901cf", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSeveral viruses cause pulmonary infections due to their shared tropism with cells of the respiratory tract . These respiratory problems due to viral infection become a public health concern due to rapid transmission through air/aerosols or via direct-indirect contact with infected persons . In addition , the cross-species transmission causes alterations to viral genetic makeup thereby increasing the risk of emergence of pathogens with new and more potent infectivity . With the introduction of effective nucleic acid-based technologies , post translational gene silencing ( PTGS ) is being increasingly used to silence viral gene targets and has shown promising approach towards management of many viral infections . Since several host factors are also utilized by these viruses during various stages of infection , silencing these host factors can also serve as promising therapeutic tool . Several nucleic acid-based technologies such as short interfering RNAs ( siRNA ) , antisense oligonucleotides , aptamers , deoxyribozymes ( DNAzymes ) , and ribozymes have been studied and used against management of respiratory viruses . These therapeutic nucleic acids can be efficiently delivered through the airways . Studies have also shown efficacy of gene therapy in clinical trials against respiratory syncytial virus ( RSV ) as well as models of respiratory diseases including severe acute respiratory syndrome ( SARS ) , measles and influenza . In this review , we have summarized some of the recent advancements made in the area of nucleic acid based therapeutics and highlighted the emerging roles of nucleic acids in the management of some of the severe respiratory viral infections . We have also focused on the methods of their delivery and associated challenges .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Several viruses cause pulmonary infections due to their shared tropism with cells of the respiratory tract .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"These respiratory problems due to viral infection become a public health concern due to rapid transmission through air/aerosols or via direct-indirect contact with infected persons .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"In addition , the cross-species transmission causes alterations to viral genetic makeup thereby increasing the risk of emergence of pathogens with new and more potent infectivity .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"With the introduction of effective nucleic acid-based technologies ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"post translational gene silencing ( PTGS ) is being increasingly used to silence viral gene targets and has shown promising approach towards management of many viral infections .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Since several host factors are also utilized by these viruses during various stages of infection ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"silencing these host factors can also serve as promising therapeutic tool .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"Several nucleic acid-based technologies such as short interfering RNAs ( siRNA ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"antisense oligonucleotides , aptamers , deoxyribozymes ( DNAzymes ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"and ribozymes have been studied and used against management of respiratory viruses .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"These therapeutic nucleic acids can be efficiently delivered through the airways .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"Studies have also shown efficacy of gene therapy in clinical trials against respiratory syncytial virus ( RSV ) as well as models of respiratory diseases including severe acute respiratory syndrome ( SARS ) , measles and influenza .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"In this review , we have summarized some of the recent advancements made in the area of nucleic acid based therapeutics and highlighted the emerging roles of nucleic acids in the management of some of the severe respiratory viral infections .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 13}, {\"segment_text\": \"We have also focused on the methods of their delivery and associated challenges .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 14}]}"}]}
{"paper_id": "63623d3ca9054b31d5a336d6f5c421b1b8503de1", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nEvaluation Surveillance system Communicable diseases Epidemiology s u m m a r y Objectives : A sentinel surveillance system ( SSS ) was set up in Hong Kong to monitor hand , foot and mouth disease ( HFMD ) trends . This evaluation assessed the performance of the SSS from 2001 to 2009 , and aimed to identify areas for improvement . Study design : A retrospective review using structured guidelines for evaluating public health surveillance systems published by the US Centers for Disease Control and Prevention . Methods : The effectiveness of the SSS was evaluated using routine service statistics , laboratory surveillance data , and results of an acceptability survey conducted among the sentinel doctors . This information was used to assess various attributes of the SSS including simplicity , flexibility , data quality , usefulness , sensitivity , specificity , positive predictive value ( PPV ) , representativeness , timeliness and acceptability . Results : The SSS was simple and flexible with high-quality data . It correlated well with the laboratory surveillance data ( P < 0.001 ) and facilitated early detection of community epidemics . It helped to identify seasonal trends and high-risk groups . Specificity was high ( 83.4 e88 .5 % ) , while sensitivity and PPV were borderline satisfactory ( 38.4 e56 .8 % ) . The sentinel clinics were representative of the population distribution . The SSS was acceptable to the sentinel doctors , but 17.9 e28 .2 % of them had delays in reporting . The SSS is effective for monitoring HFMD trends in Hong Kong , and is useful for initiating preventive measures .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Evaluation Surveillance system Communicable diseases Epidemiology s u m m a r y Objectives : A sentinel surveillance system ( SSS ) was set up in Hong Kong to monitor hand ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"foot and mouth disease ( HFMD ) trends .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"This evaluation assessed the performance of the SSS from 2001 to 2009 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"and aimed to identify areas for improvement .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Study design : A retrospective review using structured guidelines for evaluating public health surveillance systems published by the US Centers for Disease Control and Prevention .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Methods : The effectiveness of the SSS was evaluated using routine service statistics ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"laboratory surveillance data , and results of an acceptability survey conducted among the sentinel doctors .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"This information was used to assess various attributes of the SSS including simplicity ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"flexibility , data quality , usefulness ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"sensitivity , specificity , positive predictive value ( PPV ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"representativeness , timeliness and acceptability .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Results : The SSS was simple and flexible with high-quality data .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"It correlated well with the laboratory surveillance data ( P < 0.001 ) and facilitated early detection of community epidemics .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"It helped to identify seasonal trends and high-risk groups .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"Specificity was high ( 83.4 e88 .5 % ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"while sensitivity and PPV were borderline satisfactory ( 38.4 e56 .8 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"The sentinel clinics were representative of the population distribution .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"The SSS was acceptable to the sentinel doctors ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"but 17.9 e28 .2 % of them had delays in reporting .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"The SSS is effective for monitoring HFMD trends in Hong Kong ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"and is useful for initiating preventive measures .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}]}"}]}
{"paper_id": "b1735d2bf2120775db46e1803d1c92023d22e60d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nLower respiratory tract infections by respiratory syncytial virus ( RSV ) are the foremost cause of infant hospitalization and are implicated in lasting pulmonary impairment and the development of asthma . Neutrophils infiltrate the airways of pediatric patients with RSV-induced bronchiolitis in vast numbers : approximately 80 % of infiltrated cells are neutrophils . However , why neutrophils are recruited to the site of viral respiratory tract infection is not clear . In this review we discuss the beneficial and pathologic contributions of neutrophils to the immune response against RSV infection . Neutrophils can limit viral replication and spread , as well as stimulate an effective antiviral adaptive immune response . However , low specificity of neutrophil antimicrobial armaments allows for collateral tissue damage . Neutrophilinduced injury to the airways during the delicate period of infant lung development has lasting adverse consequences for pulmonary architecture and might promote the onset of asthma in susceptible subjects . We suggest that pharmacologic modulation of neutrophils should be explored as a viable future therapy for severe RSV-induced bronchiolitis and thereby prevent the inception of subsequent asthma . The antiviral functions of neutrophils suggest that targeting of neutrophils in patients with RSV-induced bronchiolitis is best performed under the umbrella of antiviral treatment . ( J Allergy Clin Immunol 2015 ; 136:838-47 . )\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Lower respiratory tract infections by respiratory syncytial virus ( RSV ) are the foremost cause of infant hospitalization and are implicated in lasting pulmonary impairment and the development of asthma .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Neutrophils infiltrate the airways of pediatric patients with RSV-induced bronchiolitis in vast numbers : approximately 80 % of infiltrated cells are neutrophils .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"However , why neutrophils are recruited to the site of viral respiratory tract infection is not clear .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"In this review we discuss the beneficial and pathologic contributions of neutrophils to the immune response against RSV infection .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Neutrophils can limit viral replication and spread ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"as well as stimulate an effective antiviral adaptive immune response .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"However , low specificity of neutrophil antimicrobial armaments allows for collateral tissue damage .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Neutrophilinduced injury to the airways during the delicate period of infant lung development has lasting adverse consequences for pulmonary architecture and might promote the onset of asthma in susceptible subjects .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"We suggest that pharmacologic modulation of neutrophils should be explored as a viable future therapy for severe RSV-induced bronchiolitis and thereby prevent the inception of subsequent asthma .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"The antiviral functions of neutrophils suggest that targeting of neutrophils in patients with RSV-induced bronchiolitis is best performed under the umbrella of antiviral treatment .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"( J Allergy Clin Immunol 2015 ; 136:838-47 . )\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 11}]}"}]}
{"paper_id": "9845bc68cd21cd2aac1db613d18336cab2420409", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nNeonatal Jersey calves ( n = 96 ) were used to evaluate effects of housing ( individual hutches or wooden pens in a barn ) and colostrum feeding ( calves were separated from the dam and fed 2 L of colostrum in nipple-bottles or allowed to nurse the dam for 3 d ) on the prevalence of selected organisms in feces . Prevalence of Cryptosporidium and Eimeria were reduced , and prevalence of rotavirus tended to be reduced , when calves were housed in hutches . Prevalence of coronavirus was unaffected by treatment . Weekly prevalence of Giardia was increased when calves were left to nurse the dam for 3 d. Mean prevalence of Cryprosporidia ( wk 1 to 4 ) , Eimeria ( wk 4 to 5 ) , Giardia , rotavirus , and coronavirus ( wk 1 to 5 ) were 34.7 , 20.6 , 27.1 , 15.8 , and 4.9 % , respectively . Escherichia coli ( K99 positive ) were observed in 3 of 174 samples cultured . Methods of housing and colostrum feeding affected acquisition of enteropathogens in this study . (\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Neonatal Jersey calves ( n = 96 ) were used to evaluate effects of housing ( individual hutches or wooden pens in a barn ) and colostrum feeding ( calves were separated from the dam and fed 2 L of colostrum in nipple-bottles or allowed to nurse the dam for 3 d ) on the prevalence of selected organisms in feces .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 1}, {\"segment_text\": \"Prevalence of Cryptosporidium and Eimeria were reduced ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"and prevalence of rotavirus tended to be reduced ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"when calves were housed in hutches .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Prevalence of coronavirus was unaffected by treatment .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Weekly prevalence of Giardia was increased when calves were left to nurse the dam for 3 d. Mean prevalence of Cryprosporidia ( wk 1 to 4 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Eimeria ( wk 4 to 5 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Giardia , rotavirus , and coronavirus ( wk 1 to 5 ) were 34.7 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"20.6 , 27.1 , 15.8 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"and 4.9 % , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Escherichia coli ( K99 positive ) were observed in 3 of 174 samples cultured .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Methods of housing and colostrum feeding affected acquisition of enteropathogens in this study .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"(\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 13}]}"}]}
{"paper_id": "544f23d64a007c69bc637743a3ebe7809d9c9c69", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nmedRxiv preprint Interpretation Parameters that successfully reproduce the observed number of cases indicate that both R 0 and the prevalence of the virus might be underestimated . This is in concordance with the newest research on undocumented COVID-19 cases . Consequently , the actual mortality rate is putatively lower than estimated . Confirmation of the pandemic characteristic by further refinement of the model and screening tests is crucial for developing an effective strategy for the global epidemiological crisis . 1 Balcan D , Gonçalves B , Hu H , Ramasco JJ , Colizza V , Vespignani A. Modeling the spatial spread of infectious diseases : the GLobal Epidemic and Mobility computational model . J Comput Sci 2010 ; 1 : 132-45 . 2 Van den Broeck W , Gioannini C , Gonçalves B , Quaggiotto M , Colizza V , Vespignani A . The GLEaMviz computational tool , a publicly available software to explore realistic epidemic spreading scenarios at the global scale . BMC Infect Dis 2011 ; 11 : 37 . 3 Tizzoni M , Bajardi P , Poletto C , et al. . Real-time numerical forecast of global epidemic spreading : case study of 2009 A/H1N1pdm . BMC Med 2012 ;\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"medRxiv preprint Interpretation Parameters that successfully reproduce the observed number of cases indicate that both R 0 and the prevalence of the virus might be underestimated .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 1}, {\"segment_text\": \"This is in concordance with the newest research on undocumented COVID-19 cases .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"Consequently , the actual mortality rate is putatively lower than estimated .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"Confirmation of the pandemic characteristic by further refinement of the model and screening tests is crucial for developing an effective strategy for the global epidemiological crisis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"1 Balcan D , Gonçalves B ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 5}, {\"segment_text\": \"Hu H , Ramasco JJ ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 6}, {\"segment_text\": \"Colizza V , Vespignani A. Modeling the spatial spread of infectious diseases : the GLobal Epidemic and Mobility computational model .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 7}, {\"segment_text\": \"J Comput Sci 2010 ; 1 : 132-45 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 8}, {\"segment_text\": \"2 Van den Broeck W ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 9}, {\"segment_text\": \"Gioannini C , Gonçalves B ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 10}, {\"segment_text\": \"Quaggiotto M , Colizza V , Vespignani A .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 11}, {\"segment_text\": \"The GLEaMviz computational tool , a publicly available software to explore realistic epidemic spreading scenarios at the global scale .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 12}, {\"segment_text\": \"BMC Infect Dis 2011 ; 11 : 37 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 13}, {\"segment_text\": \"3 Tizzoni M , Bajardi P ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 14}, {\"segment_text\": \"Poletto C , et al. .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 15}, {\"segment_text\": \"Real-time numerical forecast of global epidemic spreading : case study of 2009 A/H1N1pdm .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 16}, {\"segment_text\": \"BMC Med 2012 ;\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 17}]}"}]}
{"paper_id": "9f87d0f127411cb1dc51dbd3041aaecc008d7b8d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRecombination is a process that unlinks neighboring loci allowing for independent evolutionary trajectories within genomes of many organisms . If not properly accounted for , recombination can compromise many evolutionary analyses . In addition , when dealing with organisms that are not obligately sexually reproducing , recombination gives insight into the rate at which distinct genetic lineages come into contact . Since June 2012 , Middle East respiratory syndrome coronavirus ( MERS-CoV ) has caused 1,106 laboratory-confirmed infections , with 421 MERS-CoV-associated deaths as of 16 April 2015 . Although bats are considered as the likely ultimate source of zoonotic betacoronaviruses , dromedary camels have been consistently implicated as the source of current human infections in the Middle East . In this article , we use phylogenetic methods and simulations to show that MERS-CoV genome has likely undergone numerous recombinations recently . Recombination in MERS-CoV implies frequent co-infection with distinct lineages of MERS-CoV , probably in camels given the current understanding of MERS-CoV epidemiology .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Recombination is a process that unlinks neighboring loci allowing for independent evolutionary trajectories within genomes of many organisms .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"If not properly accounted for ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"recombination can compromise many evolutionary analyses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"In addition , when dealing with organisms that are not obligately sexually reproducing ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"recombination gives insight into the rate at which distinct genetic lineages come into contact .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Since June 2012 , Middle East respiratory syndrome coronavirus ( MERS-CoV ) has caused 1,106 laboratory-confirmed infections ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"with 421 MERS-CoV-associated deaths as of 16 April 2015 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Although bats are considered as the likely ultimate source of zoonotic betacoronaviruses ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"dromedary camels have been consistently implicated as the source of current human infections in the Middle East .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"In this article , we use phylogenetic methods and simulations to show that MERS-CoV genome has likely undergone numerous recombinations recently .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Recombination in MERS-CoV implies frequent co-infection with distinct lineages of MERS-CoV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"probably in camels given the current understanding of MERS-CoV epidemiology .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "71d2ad06792c5adb2c8fb934e9bedc53659b1dfe", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Chronic kidney disease ( CKD ) has typically a non-immune mediated origin in cats and immunecomplex glomerulonephritis ( ICGN ) is scarcely described . Aims of this study were to characterize ICGN by light and electron microscopy and identify associations with clinico-pathological findings . In addition , comparisons between cats with ICGN and non immune-complex glomerulonephritis ( non-ICGN ) were performed . Renal samples examined between 2010 and 2019 were considered if both light and electron microscopy were performed . Signalment , feline immunodeficiency virus ( FIV ) and leukemia virus ( FeLV ) status , serum creatinine concentration , urine protein-to-creatinine ( UPC ) ratio , systolic blood pressure ( SBP ) and International Renal Interest Society ( IRIS ) stage were retrieved and used for comparisons . Results : Sixty-eight client-owned cats were included . Thirty-seven cats ( 54.4 % ) had ICGN and 31 ( 45.6 % ) non-ICGN . Eighteen ( 48.6 % ) with ICGN had membranous glomerulonephropathy ( MGN ) , 14 ( 37.8 % ) membranoproliferative glomerulonephritis ( MPGN ) , and 5 ( 13.5 % ) mesangioproliferative glomerulonephritis ( MeGN ) . Clinico-pathological data were not associated with any type of ICGN . Among cats with non-ICGN , 11 ( 35.5 % ) had end-stage CKD , 9 ( 29 % ) focal segmental glomerulosclerosis , 6 ( 19.4 % ) global and multifocal mesangiosclerosis , 2 ( 6.5 % ) glomerular atrophy , 2 ( 6.5 % ) renal dysplasia and 1 ( 3.1 % ) amyloidosis . Eight ( 25.8 % ) cats with non-ICGN had chronic interstitial nephritis ( CIN ) grade 1 , 13 ( 41.9 % ) grade 2 and 10 ( 32.3 % ) grade 3 ; creatinine and UPC ratio increased with CIN grades ( p = 0.001 , p < 0.001 ) . Cats with ICGN were more frequently FIV or FeLV-infected ( OR : 11.4 ; 95 % CI : 1.4-94.4 ; p = 0.024 ) , had higher UPC ratio ( OR : 6.8 ; 95 % CI : 2.5-18.2 ; p < 0.001 ) and were younger ( OR : 0.9 ; 95 % CI : 0.7-1.0 ; p = 0.042 ) than cats with non-ICGN . Conclusions : MGN and MPGN were the most common morphological diagnoses of ICGN in cats . Unfortunately , none of the investigated findings differentiated ICGN morphological diagnoses . Serum creatinine concentration and UPC ratio were directly associated with grades of CIN ( p = 0.001 and p < 0.001 , respectively ) , confirming previous literature . More ICGN than non-ICGN was observed in cats with retroviral infections , younger cats and higher UPC ratio .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Chronic kidney disease ( CKD ) has typically a non-immune mediated origin in cats and immunecomplex glomerulonephritis ( ICGN ) is scarcely described .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Aims of this study were to characterize ICGN by light and electron microscopy and identify associations with clinico-pathological findings .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"In addition , comparisons between cats with ICGN and non immune-complex glomerulonephritis ( non-ICGN ) were performed .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Renal samples examined between 2010 and 2019 were considered if both light and electron microscopy were performed .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Signalment , feline immunodeficiency virus ( FIV ) and leukemia virus ( FeLV ) status ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"serum creatinine concentration , urine protein-to-creatinine ( UPC ) ratio ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"systolic blood pressure ( SBP ) and International Renal Interest Society ( IRIS ) stage were retrieved and used for comparisons .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Results : Sixty-eight client-owned cats were included .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Thirty-seven cats ( 54.4 % ) had ICGN and 31 ( 45.6 % ) non-ICGN .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Eighteen ( 48.6 % ) with ICGN had membranous glomerulonephropathy ( MGN ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"14 ( 37.8 % ) membranoproliferative glomerulonephritis ( MPGN ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and 5 ( 13.5 % ) mesangioproliferative glomerulonephritis ( MeGN ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Clinico-pathological data were not associated with any type of ICGN .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Among cats with non-ICGN , 11 ( 35.5 % ) had end-stage CKD ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"9 ( 29 % ) focal segmental glomerulosclerosis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"6 ( 19.4 % ) global and multifocal mesangiosclerosis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"2 ( 6.5 % ) glomerular atrophy ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"2 ( 6.5 % ) renal dysplasia and 1 ( 3.1 % ) amyloidosis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Eight ( 25.8 % ) cats with non-ICGN had chronic interstitial nephritis ( CIN ) grade 1 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"13 ( 41.9 % ) grade 2 and 10 ( 32.3 % ) grade 3 ; creatinine and UPC ratio increased with CIN grades ( p = 0.001 , p < 0.001 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"Cats with ICGN were more frequently FIV or FeLV-infected ( OR : 11.4 ; 95 % CI : 1.4-94.4 ; p = 0.024 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"had higher UPC ratio ( OR : 6.8 ; 95 % CI : 2.5-18.2 ; p < 0.001 ) and were younger ( OR : 0.9 ; 95 % CI : 0.7-1.0 ; p = 0.042 ) than cats with non-ICGN .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"Conclusions : MGN and MPGN were the most common morphological diagnoses of ICGN in cats .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"Unfortunately , none of the investigated findings differentiated ICGN morphological diagnoses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}, {\"segment_text\": \"Serum creatinine concentration and UPC ratio were directly associated with grades of CIN ( p = 0.001 and p < 0.001 , respectively ) , confirming previous literature .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 25}, {\"segment_text\": \"More ICGN than non-ICGN was observed in cats with retroviral infections ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 26}, {\"segment_text\": \"younger cats and higher UPC ratio .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 27}]}"}]}
{"paper_id": "a25094543b9d2010393d10dc4b70eb9fe0fbf159", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMedicinal plants have been used worldwide for centuries to maintain health and to treat diseases , more so chronic diseases . However , adulteration and use of spurious materials as substitutes have become a major concern for users and industry for reasons of safety and efficacy . Therefore , authentication of medicinal plants is of utmost importance . Morphological , anatomical , chemical and DNA markers solve the problem by differentiating the genuine material from the adulterants , substitutes and spurious drugs . DNA markers use nucleotide sequences to identify species ; it takes preference over the other two markers being not age dependent , tissue specific and having a higher discriminating power . Therefore , characterization of plants with such markers is an ideal approach for identification of medicinal plant species and populations/varieties of the same species . Availability of certified taxonomic specimens in herbaria is certainly required for unambiguous confirmation through final visual comparison and analysis .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Medicinal plants have been used worldwide for centuries to maintain health and to treat diseases , more so chronic diseases .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"However , adulteration and use of spurious materials as substitutes have become a major concern for users and industry for reasons of safety and efficacy .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Therefore , authentication of medicinal plants is of utmost importance .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Morphological , anatomical , chemical and DNA markers solve the problem by differentiating the genuine material from the adulterants , substitutes and spurious drugs .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"DNA markers use nucleotide sequences to identify species ; it takes preference over the other two markers being not age dependent ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"tissue specific and having a higher discriminating power .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Therefore , characterization of plants with such markers is an ideal approach for identification of medicinal plant species and populations/varieties of the same species .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Availability of certified taxonomic specimens in herbaria is certainly required for unambiguous confirmation through final visual comparison and analysis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}]}"}]}
{"paper_id": "107824986103d1409f047ec9823d75b7b25d9702", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : China 's one-child-per-couple policy , introduced in 1979 , led to profound demographic changes for nearly a quarter of the world 's population . Several decades later , the consequences include decreased fertility rates , population aging , decreased household sizes , changes in family structure , and imbalanced sex ratios . The epidemiology of communicable diseases may have been affected by these changes since the transmission dynamics of infectious diseases depend on demographic characteristics of the population . Of particular interest is influenza because China and Southeast Asia lie at the center of a global transmission network of influenza . Moreover , changes in household structure may affect influenza transmission . Is it possible that the pronounced demographic changes that have occurred in China have affected influenza transmission ? Methods and Findings : To address this question , we developed a continuous-time , stochastic , individual-based simulation model for influenza transmission . With this model , we simulated 30 years of influenza transmission and compared influenza transmission rates in populations with and without the one-child policy control . We found that the average annual attack rate is reduced by 6.08 % ( SD 2.21 % ) in the presence of the one-child policy compared to a population in which no demographic changes occurred . There was no discernible difference in the secondary attack rate , 20.15 % ( SD 1.85 % ) , between the populations with and without a one-child policy . We also forecasted influenza transmission over a ten-year time period in a population with a two-child policy under a hypothesis that a two-child-per-couple policy will be carried out in 2015 , and found a negligible difference in the average annual attack rate compared to the population with the one-child policy . Conclusions : This study found that the average annual attack rate is slightly lowered in a population with a one-child policy , which may have resulted from a decrease in household size and the proportion of children in the population .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : China 's one-child-per-couple policy ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"introduced in 1979 , led to profound demographic changes for nearly a quarter of the world 's population .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Several decades later , the consequences include decreased fertility rates ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"population aging , decreased household sizes ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"changes in family structure , and imbalanced sex ratios .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"The epidemiology of communicable diseases may have been affected by these changes since the transmission dynamics of infectious diseases depend on demographic characteristics of the population .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Of particular interest is influenza because China and Southeast Asia lie at the center of a global transmission network of influenza .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Moreover , changes in household structure may affect influenza transmission .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"Is it possible that the pronounced demographic changes that have occurred in China have affected influenza transmission ?\", \"label\": \"purpose\", \"decision_reference\": \"boundary background_vs_purpose\", \"id\": 9}, {\"segment_text\": \"Methods and Findings : To address this question ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"we developed a continuous-time , stochastic ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"individual-based simulation model for influenza transmission .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"With this model , we simulated 30 years of influenza transmission and compared influenza transmission rates in populations with and without the one-child policy control .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"We found that the average annual attack rate is reduced by 6.08 % ( SD 2.21 % ) in the presence of the one-child policy compared to a population in which no demographic changes occurred .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"There was no discernible difference in the secondary attack rate ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"20.15 % ( SD 1.85 % ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"between the populations with and without a one-child policy .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"We also forecasted influenza transmission over a ten-year time period in a population with a two-child policy under a hypothesis that a two-child-per-couple policy will be carried out in 2015 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"and found a negligible difference in the average annual attack rate compared to the population with the one-child policy .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Conclusions : This study found that the average annual attack rate is slightly lowered in a population with a one-child policy ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"which may have resulted from a decrease in household size and the proportion of children in the population .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}]}"}]}
{"paper_id": "b9e7e99d058c1fffd687046fe2999ebdba9edd65", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRegulations are a part of life but who writes them , what is the basis on which they are written and when the regulations get it wrong , whose fault is it ? Is it those who wrote the regulations , those enforcing the regulations , those being regulated or the science underpinning the regulations ? In seeking answers to these questions , this paper explores the regulatory process and the contribution of science . It takes as examples the role of the Australian Pesticides and Veterinary Medicines Authority ( APVMA ) in regulating veterinary products , of the Security Sensitive Biological Agents regulations in managing the risks from specific pathogens , the Quarantine Act regulations as applied to containment facilities and the development of welfare standards . By dealing with products , pathogens , places and `` pets '' it provides a broad oversight of how regulations have been developed and applied from different perspectives and highlights the differing roles that science and research play both in developing policy and regulations . What is clear is that in the presence of good science it is usually possible to develop sound and defensible regulations e.g. those managed by APVMA , but when there is a lack of science to underpin the regulations , problems can arise e.g. in the case of animal welfare .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Regulations are a part of life but who writes them ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"what is the basis on which they are written and when the regulations get it wrong , whose fault is it ?\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Is it those who wrote the regulations ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"those enforcing the regulations , those being regulated or the science underpinning the regulations ?\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"In seeking answers to these questions ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"this paper explores the regulatory process and the contribution of science .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"It takes as examples the role of the Australian Pesticides and Veterinary Medicines Authority ( APVMA ) in regulating veterinary products ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"of the Security Sensitive Biological Agents regulations in managing the risks from specific pathogens ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"the Quarantine Act regulations as applied to containment facilities and the development of welfare standards .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"By dealing with products , pathogens ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"places and `` pets '' it provides a broad oversight of how regulations have been developed and applied from different perspectives and highlights the differing roles that science and research play both in developing policy and regulations .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"What is clear is that in the presence of good science it is usually possible to develop sound and defensible regulations e.g. those managed by APVMA ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"but when there is a lack of science to underpin the regulations ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"problems can arise e.g. in the case of animal welfare .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}]}"}]}
{"paper_id": "83d82d42b92c964ba7bd7bd9f456a16c9d3cbaaf", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe adaptive immune response is necessary for the development of protective immunity against infectious diseases . Porcine reproductive and respiratory syndrome virus ( PRRSV ) , a genetically heterogeneous and rapidly evolving RNA virus , is the most burdensome pathogen of swine health and wellbeing worldwide . Viral infection induces antigen-specific immunity that ultimately clears the infection . However , the resulting immune memory , induced by virulent or attenuated vaccine viruses , is inconsistently protective against diverse viral strains . The immunological mechanisms by which primary and memory protection are generated and used are not well understood . Here , we summarize current knowledge regarding cellular and humoral components of the adaptive immune response to PRRSV infection that mediate primary and memory immune protection against viruses .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The adaptive immune response is necessary for the development of protective immunity against infectious diseases .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Porcine reproductive and respiratory syndrome virus ( PRRSV ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"a genetically heterogeneous and rapidly evolving RNA virus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"is the most burdensome pathogen of swine health and wellbeing worldwide .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Viral infection induces antigen-specific immunity that ultimately clears the infection .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"However , the resulting immune memory ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"induced by virulent or attenuated vaccine viruses ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"is inconsistently protective against diverse viral strains .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"The immunological mechanisms by which primary and memory protection are generated and used are not well understood .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"Here , we summarize current knowledge regarding cellular and humoral components of the adaptive immune response to PRRSV infection that mediate primary and memory immune protection against viruses .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 10}]}"}]}
{"paper_id": "8320b73d383b7b40d90992351834ac5b6df58fdf", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe NIC in Lyon has been involved in the virological diagnosis of suspect severe acute respiratory syndrome ( SARS ) patients . In March , the French medical authorities organized a medical surveillance of the medical staff who had returned from the French hospital in Hanoi . Each person presenting or not with respiratory symptoms was sampled systematically by the nearest general practitioner ( GP ) belonging to the influenza network surveillance in the community called GROG and the samples were sent to the NICs located either in Paris or in Lyon . We also received samples from patients hospitalized in the south of France suffering from acute respiratory infection soon after a journey in Asia . We implemented a PCR diagnosis for the human respiratory viruses : influenza A and B , Parainfluenza ( Type 1 to Type 4 ) , Metapneumovirus , RSV , Rhinovirus , Enterovirus , Adenovirus . In April , we set up the PCR detection of the SARS-associated coronavirus Urbani strain . The practitioners performed respiratory samples . From 14 March to 15 May we received and tested 88 respiratory samples , respectively , 19 were realized by GPs from the community network and 69 came from hospitalized patients . We never detected the urbani coronavirus strain . However , we detected respiratory viruses in 24 % of the cases : the most frequent virus was influenza A H3N2 ( 11 % ) and Parainfluenza type 3 ( 8 % ) . RSV , influenza A H1N1 and Rhinovirus were also detected 2 , 1 and 1 cases , respectively . All the positive samples except the rhinovirus came from hospitalized patients . The patients were sampled once and all of them recovered rapidly . D\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The NIC in Lyon has been involved in the virological diagnosis of suspect severe acute respiratory syndrome ( SARS ) patients .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"In March , the French medical authorities organized a medical surveillance of the medical staff who had returned from the French hospital in Hanoi .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Each person presenting or not with respiratory symptoms was sampled systematically by the nearest general practitioner ( GP ) belonging to the influenza network surveillance in the community called GROG and the samples were sent to the NICs located either in Paris or in Lyon .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"We also received samples from patients hospitalized in the south of France suffering from acute respiratory infection soon after a journey in Asia .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"We implemented a PCR diagnosis for the human respiratory viruses : influenza A and B ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Parainfluenza ( Type 1 to Type 4 ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Metapneumovirus , RSV , Rhinovirus , Enterovirus , Adenovirus .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"In April , we set up the PCR detection of the SARS-associated coronavirus Urbani strain .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The practitioners performed respiratory samples .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"From 14 March to 15 May we received and tested 88 respiratory samples ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"respectively , 19 were realized by GPs from the community network and 69 came from hospitalized patients .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"We never detected the urbani coronavirus strain .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"However , we detected respiratory viruses in 24 % of the cases : the most frequent virus was influenza A H3N2 ( 11 % ) and Parainfluenza type 3 ( 8 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"RSV , influenza A H1N1 and Rhinovirus were also detected 2 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"1 and 1 cases , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"All the positive samples except the rhinovirus came from hospitalized patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"The patients were sampled once and all of them recovered rapidly .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"D\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 18}]}"}]}
{"paper_id": "3e92c95edae9eabec9e6b1f3d8c93035ea2c9e05", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAt least 20-50 % of all ICU admissions occur in patients older than 65 years of age , and geriatric patients account for almost 60 % of all ICU days . Unfortunately , many older patients ' fi nal days are spent in the ICU ; 40 % of Medicare patients who die are admitted to an ICU during their terminal illness , accounting for 25 % of all Medicare expenditures . Additionally , of those who survive , many are discharged to a subacute facility with persistent organ failure where they will eventually die . Furthermore , those discharged to a subacute care facility have a higher mortality rate compared to those discharged home ( 31 vs. 17 % ) . The decision to admit an elderly patient to an ICU should be based not only on their comorbidities , acuity of illness , and prehospital functional status , including quality of life , but also on their preference for the use of life-sustaining treatments if it is known . The underlying disease process is not altered despite the use of invasive procedures in terminally ill patients , and potential harm or discomfort can occur if invasive procedures are used inappropriately . To avoid such unintended consequences and enhance optimal end-of-life decision making , healthcare providers need to identify , explain , and negotiate consensus therapeutic goals . In 2005 , spending by Medicare for those older than 65 years totaled $ 342 billion , representing 17.1 % of the total of $ 2 trillion spent nationwide for health care . Intensive care consumes 4 % of national healthcare expenditures . During the last 6 months of their lives , 11 % of Medicare recipients spend 8 or more days in the ICU ; various studies documenting ICU occupancy by those older than 65 years old note that this ranges from one quarter to one half of the available beds . These statistics alone show the profound fi nancial burden that must be borne to provide a medically sound and appropriate depth of care , a signi fi cant portion of which will be provided in the ICU .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"At least 20-50 % of all ICU admissions occur in patients older than 65 years of age ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"and geriatric patients account for almost 60 % of all ICU days .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Unfortunately , many older patients ' fi nal days are spent in the ICU ; 40 % of Medicare patients who die are admitted to an ICU during their terminal illness ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"accounting for 25 % of all Medicare expenditures .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Additionally , of those who survive ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"many are discharged to a subacute facility with persistent organ failure where they will eventually die .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"Furthermore , those discharged to a subacute care facility have a higher mortality rate compared to those discharged home ( 31 vs. 17 % ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"The decision to admit an elderly patient to an ICU should be based not only on their comorbidities ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"acuity of illness , and prehospital functional status ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"including quality of life , but also on their preference for the use of life-sustaining treatments if it is known .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"The underlying disease process is not altered despite the use of invasive procedures in terminally ill patients ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"and potential harm or discomfort can occur if invasive procedures are used inappropriately .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"To avoid such unintended consequences and enhance optimal end-of-life decision making ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 13}, {\"segment_text\": \"healthcare providers need to identify ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 14}, {\"segment_text\": \"explain , and negotiate consensus therapeutic goals .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 15}, {\"segment_text\": \"In 2005 , spending by Medicare for those older than 65 years totaled $ 342 billion ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"representing 17.1 % of the total of $ 2 trillion spent nationwide for health care .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Intensive care consumes 4 % of national healthcare expenditures .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"During the last 6 months of their lives ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"11 % of Medicare recipients spend 8 or more days in the ICU ; various studies documenting ICU occupancy by those older than 65 years old note that this ranges from one quarter to one half of the available beds .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"These statistics alone show the profound fi nancial burden that must be borne to provide a medically sound and appropriate depth of care ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"a signi fi cant portion of which will be provided in the ICU .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}]}"}]}
{"paper_id": "4f292b626af0f6632fc307e56a378ccc52eabd8c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCLN cervical lymph node Treg regulatory T cell BALF bronchoalveolar lavage fluid a b s t r a c t Background : IL-35 was recently identified as an anti-inflammatory cytokine . We previously reported that recombinant fusion protein of murine IL-35 and human IgG1 Fc fragment ( rIL-35 ) reduced Th2 cytokines ( IL-4 and IL-5 ) in vitro . However , it is unclear whether IL-35 can attenuate nasal allergic responses and symptoms of allergic rhinitis in vivo . Methods : To investigate the in vivo effect of IL-35 on allergic rhinitis in mice , mice were sensitized with ovalbumin ( OVA ) . Intranasal administration of rIL-35 and intranasal challenge of OVA were then performed . Nasal symptoms were estimated after the last nasal challenge . Nasal tissue and cervical lymph nodes ( CLN ) were collected . OVA-specific IgE in sera , OVA-specific T cell response , and the production of cytokines ( IL-4 , IL-5 , and IL-10 ) stimulated by the OVA antigen were measured . The transcription level of Foxp3 and the frequency of CD4 þ CD25 þ regulatory T cells were also measured . Results : rIL-35 significantly inhibited the number of sneezes and nasal rubbing movements . It also reduced the number of eosinophils in the nasal mucosa and significantly decreased the level of OVAspecific IgE , the OVA-specific T cell proliferation , and the production of IL-4 and IL-5 . Furthermore , rIL-35 significantly increased the production of IL-10 , the transcription level of Foxp3 , and the frequency of CD4 þ CD25 þ regulatory T cells . Conclusions : This study showed for the first time that rIL-35 inhibits nasal allergic responses and symptoms in mice , and that rIL-35 increases IL-10 , Foxp3 , and CD4 þ CD25 þ regulatory T cells in CLN . This study also suggests that intranasal administration of IL-35 can attenuate allergic rhinitis .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"CLN cervical lymph node Treg regulatory T cell BALF bronchoalveolar lavage fluid a b s t r a c t Background : IL-35 was recently identified as an anti-inflammatory cytokine .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"We previously reported that recombinant fusion protein of murine IL-35 and human IgG1 Fc fragment ( rIL-35 ) reduced Th2 cytokines ( IL-4 and IL-5 ) in vitro .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"However , it is unclear whether IL-35 can attenuate nasal allergic responses and symptoms of allergic rhinitis in vivo .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Methods : To investigate the in vivo effect of IL-35 on allergic rhinitis in mice ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"mice were sensitized with ovalbumin ( OVA ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Intranasal administration of rIL-35 and intranasal challenge of OVA were then performed .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Nasal symptoms were estimated after the last nasal challenge .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Nasal tissue and cervical lymph nodes ( CLN ) were collected .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"OVA-specific IgE in sera , OVA-specific T cell response ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"and the production of cytokines ( IL-4 , IL-5 , and IL-10 ) stimulated by the OVA antigen were measured .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"The transcription level of Foxp3 and the frequency of CD4 þ CD25 þ regulatory T cells were also measured .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Results : rIL-35 significantly inhibited the number of sneezes and nasal rubbing movements .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"It also reduced the number of eosinophils in the nasal mucosa and significantly decreased the level of OVAspecific IgE ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"the OVA-specific T cell proliferation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"and the production of IL-4 and IL-5 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Furthermore , rIL-35 significantly increased the production of IL-10 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"the transcription level of Foxp3 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"and the frequency of CD4 þ CD25 þ regulatory T cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Conclusions : This study showed for the first time that rIL-35 inhibits nasal allergic responses and symptoms in mice ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"and that rIL-35 increases IL-10 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"Foxp3 , and CD4 þ CD25 þ regulatory T cells in CLN .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"This study also suggests that intranasal administration of IL-35 can attenuate allergic rhinitis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}]}"}]}
{"paper_id": "b1bb28f5ec512dd9cacffd54b6e8dd6646fe4fc5", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCoronaviruses have a wide host range and can cause a variety of diseases with varying severity in different animals . Several enteric coronaviruses have been identified that are associated with diarrhea in swine and that have caused substantial economic losses . In this study , a newly emerged porcine enteric alphacoronavirus ( PEAV ) , PEAV-GD-CH/2017 , was identified from suckling piglets with diarrhea in southern China , and a fulllength genome sequence of PEAV was obtained for systematic analysis . The novel PEAV sequence was most identical to that of bat-HKU2 , and the differences between them were comprehensively compared , especially the uniform features of the S protein , which was shown to have a close relationship with betacoronaviruses and to perhaps represent unrecognized betacoronaviruses . In addition , Bayesian analysis was conducted to address the origin of PEAV , and the divergence time between PEAV and bat-HKU2 was estimated at 1926 , which indicates that PEAV is not newly emerged and may have circulated in swine herds for several decades since the interspecies transmission of this coronavirus from bat to swine . The evolutionary rate of coronaviruses was estimated to be 1.93 × 10 − 4 substitutions per site per year for the RdRp gene in our analysis . For the origin of PEAV , we suspect that it is the result of the interspecies transmission of bat-HKU2 from bat to swine . Our results provide valuable information about the uniform features , origin and evolution of the novel PEAV , which will facilitate further investigations of this newly emerged pathogen .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Coronaviruses have a wide host range and can cause a variety of diseases with varying severity in different animals .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Several enteric coronaviruses have been identified that are associated with diarrhea in swine and that have caused substantial economic losses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"In this study , a newly emerged porcine enteric alphacoronavirus ( PEAV ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"PEAV-GD-CH/2017 , was identified from suckling piglets with diarrhea in southern China ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"and a fulllength genome sequence of PEAV was obtained for systematic analysis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"The novel PEAV sequence was most identical to that of bat-HKU2 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"and the differences between them were comprehensively compared ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"especially the uniform features of the S protein ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"which was shown to have a close relationship with betacoronaviruses and to perhaps represent unrecognized betacoronaviruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"In addition , Bayesian analysis was conducted to address the origin of PEAV ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"and the divergence time between PEAV and bat-HKU2 was estimated at 1926 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"which indicates that PEAV is not newly emerged and may have circulated in swine herds for several decades since the interspecies transmission of this coronavirus from bat to swine .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"The evolutionary rate of coronaviruses was estimated to be 1.93 × 10 − 4 substitutions per site per year for the RdRp gene in our analysis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"For the origin of PEAV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"we suspect that it is the result of the interspecies transmission of bat-HKU2 from bat to swine .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Our results provide valuable information about the uniform features ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"origin and evolution of the novel PEAV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"which will facilitate further investigations of this newly emerged pathogen .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "778e39cb165c72b4245262781d804c4e1f6da3d7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCardiotoxicity is a well-known side effect of doxorubicin ( DOX ) , but the mechanisms leading to this phenomenon are still not completely clear . Prediction of drug-induced dysfunction onset is difficult and is still largely based on detection of cardiac troponin ( cTn ) , a circulating marker of heart damage . In the last years , several investigations focused on the possible involvement of microRNAs ( miRNAs ) in DOX-induced toxicity in vitro , with contrasting results . Recently , several groups employed animal models to mimic patient 's condition , investigate the biological pathways perturbed by DOX , and identify diagnostic markers of cardiotoxicity . We reviewed the results from several studies investigating cardiac miRNAs expression in rodent models of DOX-treatment . We also discussed the data from two publications indicating the possible use of circulating miRNA as biomarkers of DOX-induced cardiotoxicity . Unfortunately , limited information was derived from these studies , as selection methods of candidate-miRNAs and heterogeneity in cardiotoxicity assessment greatly hampered the novelty and robustness of the findings . Nevertheless , at least one circulating miRNA , miR-1 , showed a good potential as early biomarker of drug-mediated cardiac dysfunction onset . The use of animal models to investigate DOX-induced cardiotoxicity surely helps narrowing the gap between basic research and clinical practice . Despite this , several issues , including selection of relevant miRNAs and less-than-optimal assessment of cardiotoxicity , greatly limited the results obtained so far . Nonetheless , the association of patients-based studies with the use of preclinical models may be the key to address the many unanswered questions regarding the pathophysiology and early detection of cardiotoxicity .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Cardiotoxicity is a well-known side effect of doxorubicin ( DOX ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"but the mechanisms leading to this phenomenon are still not completely clear .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Prediction of drug-induced dysfunction onset is difficult and is still largely based on detection of cardiac troponin ( cTn ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"a circulating marker of heart damage .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"In the last years , several investigations focused on the possible involvement of microRNAs ( miRNAs ) in DOX-induced toxicity in vitro , with contrasting results .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Recently , several groups employed animal models to mimic patient 's condition ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"investigate the biological pathways perturbed by DOX ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"and identify diagnostic markers of cardiotoxicity .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"We reviewed the results from several studies investigating cardiac miRNAs expression in rodent models of DOX-treatment .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}, {\"segment_text\": \"We also discussed the data from two publications indicating the possible use of circulating miRNA as biomarkers of DOX-induced cardiotoxicity .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 10}, {\"segment_text\": \"Unfortunately , limited information was derived from these studies ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"as selection methods of candidate-miRNAs and heterogeneity in cardiotoxicity assessment greatly hampered the novelty and robustness of the findings .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Nevertheless , at least one circulating miRNA ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"miR-1 , showed a good potential as early biomarker of drug-mediated cardiac dysfunction onset .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"The use of animal models to investigate DOX-induced cardiotoxicity surely helps narrowing the gap between basic research and clinical practice .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Despite this , several issues ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"including selection of relevant miRNAs and less-than-optimal assessment of cardiotoxicity ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"greatly limited the results obtained so far .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Nonetheless , the association of patients-based studies with the use of preclinical models may be the key to address the many unanswered questions regarding the pathophysiology and early detection of cardiotoxicity .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}]}"}]}
{"paper_id": "b3487c94e4f80b43ee541b21249b1885a20f34ce", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPorcine group A rotavirus ( GARV ) is considered to be an important animal pathogen due to their economic impact in the swine industry and its potential to cause heterologous infections in humans . This study examined 475 fecal samples from 143 farms located in 6 provinces across South Korea . RT-PCR and nested PCR utilizing primer pairs specific for the GARV VP6 gene detected GARV-positive reactions in 182 ( 38.3 % ) diarrheic fecal samples . A total of 98 porcine GARV strains isolated from the GARV-positive feces were analyzed for G and P genotyping . Based on the sequence and phylogenetic analyses , the most predominant combination of G and P genotypes was G5P ( 7 ) , found in 63 GARV strains ( 64.3 % ) . The other combinations of G and P genotypes were G8P ( 7 ) ( 16 strains ( 16.3 % ) ) , G9P ( 7 ) ( 7 strains ( 7.1 % ) ) , G9P ( 23 ) ( 2 strains ( 2.0 % ) ) , and G8P ( 1 ) ( 1 strain ( 1.0 % ) ) . The counterparts of G or P genotypes were not determined in three G5 , five P ( 7 ) , and one P ( 1 ) strains . Interestingly , phylogenetic analysis indicated that all Korean G9 strains were more closely related to lineage VI porcine and human viruses than to other lineages ( I-V ) of GARVs and to Korean human G9 strains ( lineage III ) . These results show that porcine GARV infections are common in diarrheic piglets in South Korea . The infecting strains are genetically diverse , and include homologous ( G5P ( 7 ) ) , heterologous ( G8P ( 1 ) ) , and reassortant ( G8P ( 7 ) ) , as well as emerging G9 GARV strains . ß\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Porcine group A rotavirus ( GARV ) is considered to be an important animal pathogen due to their economic impact in the swine industry and its potential to cause heterologous infections in humans .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"This study examined 475 fecal samples from 143 farms located in 6 provinces across South Korea .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"RT-PCR and nested PCR utilizing primer pairs specific for the GARV VP6 gene detected GARV-positive reactions in 182 ( 38.3 % ) diarrheic fecal samples .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"A total of 98 porcine GARV strains isolated from the GARV-positive feces were analyzed for G and P genotyping .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Based on the sequence and phylogenetic analyses ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"the most predominant combination of G and P genotypes was G5P ( 7 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"found in 63 GARV strains ( 64.3 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"The other combinations of G and P genotypes were G8P ( 7 ) ( 16 strains ( 16.3 % ) ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"G9P ( 7 ) ( 7 strains ( 7.1 % ) ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"G9P ( 23 ) ( 2 strains ( 2.0 % ) ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"and G8P ( 1 ) ( 1 strain ( 1.0 % ) ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"The counterparts of G or P genotypes were not determined in three G5 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"five P ( 7 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"and one P ( 1 ) strains .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"Interestingly , phylogenetic analysis indicated that all Korean G9 strains were more closely related to lineage VI porcine and human viruses than to other lineages ( I-V ) of GARVs and to Korean human G9 strains ( lineage III ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"These results show that porcine GARV infections are common in diarrheic piglets in South Korea .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"The infecting strains are genetically diverse ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"and include homologous ( G5P ( 7 ) ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"heterologous ( G8P ( 1 ) ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"and reassortant ( G8P ( 7 ) ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}, {\"segment_text\": \"as well as emerging G9 GARV strains .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}, {\"segment_text\": \"ß\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 22}]}"}]}
{"paper_id": "96071f2ddd4192c50ff7bbe2c72b08f6d7210b2c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nFrom an aqueous decoction of the traditional Chinese medicine `` ban lan gen '' ( the Isatis indigotica root ) , an antiviral natural product CI -39 was isolated as an NNRTI ( non-nucleoside reverse transcriptase inhibitor ) ( EC 50 1/4 3.40 mM ) . Its novel structure was determined as methyl ( 1-methoxy-1H-indol-3-yl ) acetamidobenzoate by spectroscopic data and confirmed by single crystal X-ray diffraction . Through synthesis and structure-activity relationship ( SAR ) investigation of CI -39 and 57 new derivatives ( 24 with EC 50 values of 0.06 e8 .55 mM ) , two optimized derivatives 10f and 10i ( EC 50 : 0.06 mM and 0.06 mM ) having activity comparable to that of NVP ( EC 50 1/4 0.03 mM ) were obtained . Further evaluation verified that 10f and 10i were RT DNA polymerase inhibitors and exhibited better activities and drug resistance folds compared to NVP against seven NNRTI-resistant strains carrying different mutations . Especially , 10i ( EC 50 1/4 0.43 mM ) was more active to the L100I/K103N double-mutant strain as compared to both NVP ( EC 50 1/4 0.76 mM ) and EFV ( EC 50 1/4 1.08 mM ) . The molecular docking demonstrated a possible binding pattern between 10i and RT and revealed activity mechanism of 10i against the NNRTI-resistant strains . a Chemical shift values ( d ) were measured at 500 MHz for 1 H and at 125 MHz for 13 C , respectively . Proton coupling constants ( J ) in Hz are given in parentheses . The assignments were based on DEPT , 1 He 1 H COSY , HSQC , and HMBC experiments . C. Xu et al. .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"From an aqueous decoction of the traditional Chinese medicine `` ban lan gen '' ( the Isatis indigotica root ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"an antiviral natural product CI -39 was isolated as an NNRTI ( non-nucleoside reverse transcriptase inhibitor ) ( EC 50 1/4 3.40 mM ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Its novel structure was determined as methyl ( 1-methoxy-1H-indol-3-yl ) acetamidobenzoate by spectroscopic data and confirmed by single crystal X-ray diffraction .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Through synthesis and structure-activity relationship ( SAR ) investigation of CI -39 and 57 new derivatives ( 24 with EC 50 values of 0.06 e8 .55 mM ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"two optimized derivatives 10f and 10i ( EC 50 : 0.06 mM and 0.06 mM ) having activity comparable to that of NVP ( EC 50 1/4 0.03 mM ) were obtained .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Further evaluation verified that 10f and 10i were RT DNA polymerase inhibitors and exhibited better activities and drug resistance folds compared to NVP against seven NNRTI-resistant strains carrying different mutations .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Especially , 10i\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"( EC 50 1/4 0.43 mM ) was more active to the L100I/K103N double-mutant strain as compared to both NVP ( EC 50 1/4 0.76 mM ) and EFV ( EC 50 1/4 1.08 mM ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"The molecular docking demonstrated a possible binding pattern between 10i and RT and revealed activity mechanism of 10i against the NNRTI-resistant strains .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"a Chemical shift values ( d ) were measured at 500 MHz for 1 H and at 125 MHz for 13 C , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"Proton coupling constants ( J ) in Hz are given in parentheses .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"The assignments were based on DEPT ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"1 He 1 H COSY ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"HSQC , and HMBC experiments .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"C. Xu et al. .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 15}]}"}]}
{"paper_id": "75232f1c2ce74f3d48e406ee145b0809fc3284f0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIn 2012 , a novel coronavirus ( CoV ) associated with severe respiratory disease , Middle East respiratory syndrome ( MERS-CoV ; previously known as human coronavirus-Erasmus Medical Center or hCoV-EMC ) , emerged in the Arabian Peninsula . To date , 114 human cases of MERS-CoV have been reported , with 54 fatalities . Animal models for MERS-CoV infection of humans are needed to elucidate MERS pathogenesis and to develop vaccines and antivirals . In this study , we developed rhesus macaques as a model for MERS-CoV using intratracheal inoculation . The infected monkeys showed clinical signs of disease , virus replication , histological lesions , and neutralizing antibody production , indicating that this monkey model is suitable for studies of MERS-CoV infection .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"In 2012 , a novel coronavirus ( CoV ) associated with severe respiratory disease ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Middle East respiratory syndrome ( MERS-CoV ; previously known as human coronavirus-Erasmus Medical Center or hCoV-EMC ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"emerged in the Arabian Peninsula .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"To date , 114 human cases of MERS-CoV have been reported , with 54 fatalities .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Animal models for MERS-CoV infection of humans are needed to elucidate MERS pathogenesis and to develop vaccines and antivirals .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"In this study , we developed rhesus macaques as a model for MERS-CoV using intratracheal inoculation .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"The infected monkeys showed clinical signs of disease ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"virus replication , histological lesions ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and neutralizing antibody production , indicating that this monkey model is suitable for studies of MERS-CoV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}]}"}]}
{"paper_id": "99e6b617ea3f4d122410160e631c4021e6a8969c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nDespite the significant role of seasonal influenza vaccination in preventing and minimizing the serious complications of influenza infection in type 2 diabetes mellitus ( T2DM ) patients , unsatisfactory compliance still exists for vaccination . Study objectives were to explore the vaccination status and determinants in T2DM patients in southwestern Saudi Arabia . A cross-sectional study on a representative sample of T2DM patients in Abha city , southwestern Saudi Arabia , was conducted . Data for sociodemographic characteristics , clinical criteria , vaccination status , vaccination motivators and barriers and seasonal influenza knowledge were collected . Out of 353 T2DM patients included in the study , seasonal influenza vaccination coverage was 61 % in year 2017 . A significant factors associated with non-vaccination were ; poor influenza and its vaccine knowledge ( OR = 4.31 , 95 % CI : 2.73-6.80 ) , illiteracy ( OR = 1.93 , 95 % CI : 1.11-3.37 ) , and more than 10 years disease duration ( OR = 2.07 , 95 % CI : 1.11-3.87 ) . Presence of family history of DM and ischemic heart comorbidity minimized the possibility of non-vaccination ( OR = 0.54 and 0.28 respectively ) . Healthcare givers ' advice was the most reported vaccination motivator ( 84.7 % ) while ; fear of vaccine side effects was the most stated barrier ( 73 % ) . In conclusion , influenza vaccination rate among T2DM in the present study is less than the recommended level . Continuous primary health care center-based educational programs should be implemented to aware and encourage influenza vaccination among T2DM patients .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Despite the significant role of seasonal influenza vaccination in preventing and minimizing the serious complications of influenza infection in type 2 diabetes mellitus ( T2DM ) patients ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"unsatisfactory compliance still exists for vaccination .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Study objectives were to explore the vaccination status and determinants in T2DM patients in southwestern Saudi Arabia .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"A cross-sectional study on a representative sample of T2DM patients in Abha city ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"southwestern Saudi Arabia , was conducted .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Data for sociodemographic characteristics , clinical criteria ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"vaccination status , vaccination motivators and barriers and seasonal influenza knowledge were collected .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Out of 353 T2DM patients included in the study ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"seasonal influenza vaccination coverage was 61 % in year 2017 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"A significant factors associated with non-vaccination were ; poor influenza and its vaccine knowledge ( OR = 4.31 , 95 % CI : 2.73-6.80 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"illiteracy ( OR = 1.93 , 95 % CI : 1.11-3.37 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and more than 10 years disease duration ( OR = 2.07 , 95 % CI : 1.11-3.87 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Presence of family history of DM and ischemic heart comorbidity minimized the possibility of non-vaccination ( OR = 0.54 and 0.28 respectively ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Healthcare givers ' advice was the most reported vaccination motivator ( 84.7 % ) while ; fear of vaccine side effects was the most stated barrier ( 73 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"In conclusion , influenza vaccination rate among T2DM in the present study is less than the recommended level .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Continuous primary health care center-based educational programs should be implemented to aware and encourage influenza vaccination among T2DM patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "a4f4f45914ad5f3481a41f25238d10fe93ff66cd", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nA number of PVs have been described in bats but to the best of our knowledge not from feces . Using a previously described NetoVIR protocol , Eidolon helvum pooled fecal samples ( Eh ) were treated and sequenced by Illumina next generation sequencing technology . Two complete genomes of novel PVs ( EhPV2 and EhPV3 ) and 3 partial sequences ( BATPV61 , BATPV890a and BATPV890b ) were obtained and analysis showed that the EhPV2 and EhPV3 major capsid proteins cluster with and share 60-64 % nucleotide identity with that of Rousettus aegyptiacus PV1 , thus representing new species of PVs within the genus Psipapillomavirus . The other PVs clustered in different branches of our phylogenetic tree and may potentially represent novel species and/or genera . This points to the vast diversity of PVs in bats and in Eidolon helvum bats in particular , therefore adding support to the current concept that PV evolution is more complex than merely strict PV-host co-evolution .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"A number of PVs have been described in bats but to the best of our knowledge not from feces .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Using a previously described NetoVIR protocol ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Eidolon helvum pooled fecal samples ( Eh ) were treated and sequenced by Illumina next generation sequencing technology .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Two complete genomes of novel PVs ( EhPV2 and EhPV3 ) and 3 partial sequences ( BATPV61 , BATPV890a and BATPV890b ) were obtained and analysis showed that the EhPV2 and EhPV3 major capsid proteins cluster with and share 60-64 % nucleotide identity with that of Rousettus aegyptiacus PV1 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"thus representing new species of PVs within the genus Psipapillomavirus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"The other PVs clustered in different branches of our phylogenetic tree and may potentially represent novel species and/or genera .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"This points to the vast diversity of PVs in bats and in Eidolon helvum bats in particular ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"therefore adding support to the current concept that PV evolution is more complex than merely strict PV-host co-evolution .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}]}"}]}
{"paper_id": "cf2b21513ebe7ddeb39e48f09f3f3e6bc47b117e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMiddle East respiratory syndrome coronavirus ( MERS-CoV ) infects host cells through binding the receptor binding domain ( RBD ) on its spike glycoprotein to human receptor dipeptidyl peptidase 4 ( hDPP4 ) . Here , we report identification of critical residues on hDPP4 for RBD binding and virus entry through analysis of a panel of hDPP4 mutants . Based on the RBD-hDPP4 crystal structure we reported , the mutated residues were located at the interface between RBD and hDPP4 , which potentially changed the polarity , hydrophobic or hydrophilic properties of hDPP4 , thereby interfering or disrupting their interaction with RBD . Using surface plasmon resonance ( SPR ) binding analysis and pseudovirus infection assay , we showed that several residues in hDPP4-RBD binding interface were important on hDPP4-RBD binding and viral entry . These results provide atomic insights into the features of interactions between hDPP4 and MERS-CoV RBD , and also provide potential explanation for cellular and species tropism of MERS-CoV infection .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Middle East respiratory syndrome coronavirus ( MERS-CoV ) infects host cells through binding the receptor binding domain ( RBD ) on its spike glycoprotein to human receptor dipeptidyl peptidase 4 ( hDPP4 ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Here , we report identification of critical residues on hDPP4 for RBD binding and virus entry through analysis of a panel of hDPP4 mutants .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"Based on the RBD-hDPP4 crystal structure we reported ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"the mutated residues were located at the interface between RBD and hDPP4 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"which potentially changed the polarity ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"hydrophobic or hydrophilic properties of hDPP4 ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"thereby interfering or disrupting their interaction with RBD .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Using surface plasmon resonance ( SPR ) binding analysis and pseudovirus infection assay ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"we showed that several residues in hDPP4-RBD binding interface were important on hDPP4-RBD binding and viral entry .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"These results provide atomic insights into the features of interactions between hDPP4 and MERS-CoV RBD ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"and also provide potential explanation for cellular and species tropism of MERS-CoV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}]}"}]}
{"paper_id": "5bc4d92dcd27012532757bc3b0c55b8dff1319b9", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nA rapid one-step reverse transcription-loop-mediated isothermal amplification ( RT-LAMP ) assay targeting the pol-integrase gene was developed to detect human immunodeficiency virus type 1 ( HIV-1 ) group M . This HIV-1 RT-LAMP assay is simple and rapid , and amplification can be completed within 35 min under isothermal conditions at 60 • C . The 100 % detection limit of HIV-1 RT-LAMP was determined using a standard strain ( WHO HIV-1 ( 97/656 ) ) in octuplicate and found to be 120 copies/ml . The RT-LAMP assay was evaluated for use for clinical diagnosis using plasma samples collected from 57 HIV-1-infected and 40 uninfected individuals in Cameroon , where highly divergent HIV-1 strains are prevalent . Of the 57 samples from infected individuals , 56 harbored group-M HIV-1 strains , such as subtypes A , B , G , F2 , and circulating recombinant forms ( CRFs ) 01 , 02 , 09 , 11 , 13 ; all were RT-LAMP positive . One sample harboring group-O HIV-1 and the 40 HIV-1-uninfected samples were RT-LAMP negative . These findings indicate that HIV-1 RT-LAMP can detect HIV-1 group-M RNA from plasma samples rapidly and with high sensitivity and specificity . These data also suggest that this RT-LAMP assay can be useful for confirming HIV diagnosis , particularly in resource-limited settings .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"A rapid one-step reverse transcription-loop-mediated isothermal amplification ( RT-LAMP ) assay targeting the pol-integrase gene was developed to detect human immunodeficiency virus type 1 ( HIV-1 ) group M .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"This HIV-1 RT-LAMP assay is simple and rapid ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"and amplification can be completed within 35 min under isothermal conditions at 60 • C .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The 100 % detection limit of HIV-1 RT-LAMP was determined using a standard strain ( WHO HIV-1 ( 97/656 ) ) in octuplicate and found to be 120 copies/ml .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"The RT-LAMP assay was evaluated for use for clinical diagnosis using plasma samples collected from 57 HIV-1-infected and 40 uninfected individuals in Cameroon ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"where highly divergent HIV-1 strains are prevalent .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Of the 57 samples from infected individuals ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"56 harbored group-M HIV-1 strains ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"such as subtypes A , B ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"G , F2 , and circulating recombinant forms ( CRFs ) 01 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"02 , 09 , 11 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"13 ; all were RT-LAMP positive .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"One sample harboring group-O HIV-1 and the 40 HIV-1-uninfected samples were RT-LAMP negative .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"These findings indicate that HIV-1 RT-LAMP can detect HIV-1 group-M RNA from plasma samples rapidly and with high sensitivity and specificity .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"These data also suggest that this RT-LAMP assay can be useful for confirming HIV diagnosis , particularly in resource-limited settings .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}]}"}]}
{"paper_id": "621a2f81b5d9517781ae28d428f4e8abf0d5427a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nResting naive CD8 + T cells have an astounding capacity to react to pathogens by massive expansion and differentiation into cytotoxic effector cells that migrate to all corners of the body to clear the infection . The initial interaction with antigen-presenting cells in the central lymphoid organs drives an orchestrated program of differentiation aimed at producing sufficient numbers of effectors to get the job done without resulting in clonal exhaustion . Interactions with antigenpresenting cells and other immune cells continue at the site of infection to regulate further on-site expansion and differentiation , all with the goal of protecting the host with minimal bystander tissue damage . Here we review recent advances in CD8 + T cell recognition of antigen in lymphoid as well as in nonlymphoid tissues in the periphery , and how CD8 + T cell expansion and differentiation are controlled in these contexts .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Resting naive CD8 + T cells have an astounding capacity to react to pathogens by massive expansion and differentiation into cytotoxic effector cells that migrate to all corners of the body to clear the infection .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"The initial interaction with antigen-presenting cells in the central lymphoid organs drives an orchestrated program of differentiation aimed at producing sufficient numbers of effectors to get the job done without resulting in clonal exhaustion .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Interactions with antigenpresenting cells and other immune cells continue at the site of infection to regulate further on-site expansion and differentiation ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"all with the goal of protecting the host with minimal bystander tissue damage .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Here we review recent advances in CD8 + T cell recognition of antigen in lymphoid as well as in nonlymphoid tissues in the periphery ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"and how CD8 + T cell expansion and differentiation are controlled in these contexts .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}]}"}]}
{"paper_id": "6ab7d80bb6dc14cac7fe9c7d5a6060af434bef0a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Young children with persistent wheezing pose a diagnostic and therapeutical challenge to the pediatrician . We aimed to evaluate bacterial bronchial infection as a possible reason for non response to conventional asthma therapy , and to identify and characterise the predominant pathogens involved . Methods : We retrospectively analysed microbiological and cytological findings in a selected population of young wheezers with symptoms unresponsive to inhaled corticosteroid ( ICS ) therapy , who underwent flexible bronchoscopy with bronchoalveolar lavage ( BAL ) . Procedural measures were taken to limit contamination risk and quantitative bacterial culture of BAL fluid ( significance cut-off ≥ 10 4 colony-forming units/ml ) was used . Modern microbiological methods were used for detection of a wide panel of pathogens and for characterisation of the bacterial isolates . Results : 33 children aged between 4 and 38 months , without structural anomalies of the conductive airways were evaluated . Significant bacterial BAL cultures were found in 48,5 % of patients . Haemophilus influenzae was isolated in 30,3 % , Streptococcus pneumoniae in 12,1 % and Moraxella catarrhalis in 12,1 % . All H. influenzae isolates were non-encapsulated strains and definitely distinguished from non-haemolytic H. haemolyticus . Respiratory viruses were detected in 21,9 % of cases with mixed bacterial-viral infection in 12,1 % . Cytology revealed a marked neutrophilic inflammation . Conclusions : Bacterial infection of the bronchial tree is common in persistent preschool wheezers and provides a possible explanation for non response to ICS therapy . Non-typeable H. influenzae seems to be the predominant pathogen involved , followed by S. pneumoniae and M. catarrhalis .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Young children with persistent wheezing pose a diagnostic and therapeutical challenge to the pediatrician .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"We aimed to evaluate bacterial bronchial infection as a possible reason for non response to conventional asthma therapy ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"and to identify and characterise the predominant pathogens involved .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"Methods : We retrospectively analysed microbiological and cytological findings in a selected population of young wheezers with symptoms unresponsive to inhaled corticosteroid ( ICS ) therapy ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"who underwent flexible bronchoscopy with bronchoalveolar lavage ( BAL ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Procedural measures were taken to limit contamination risk and quantitative bacterial culture of BAL fluid ( significance cut-off ≥ 10 4 colony-forming units/ml ) was used .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Modern microbiological methods were used for detection of a wide panel of pathogens and for characterisation of the bacterial isolates .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Results : 33 children aged between 4 and 38 months ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"without structural anomalies of the conductive airways were evaluated .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Significant bacterial BAL cultures were found in 48,5 % of patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Haemophilus influenzae was isolated in 30,3 % ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Streptococcus pneumoniae in 12,1 % and Moraxella catarrhalis in 12,1 % .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"All H. influenzae isolates were non-encapsulated strains and definitely distinguished from non-haemolytic H. haemolyticus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Respiratory viruses were detected in 21,9 % of cases with mixed bacterial-viral infection in 12,1 % .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Cytology revealed a marked neutrophilic inflammation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Conclusions : Bacterial infection of the bronchial tree is common in persistent preschool wheezers and provides a possible explanation for non response to ICS therapy .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Non-typeable H. influenzae seems to be the predominant pathogen involved ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"followed by S. pneumoniae and M. catarrhalis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "0e261abc97b50372753a8415e5a6b12da8a6be05", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBiological factors that influence the host range and spillover of Ebola virus ( EBOV ) and other filoviruses remain enigmatic . While filoviruses infect diverse mammalian cell lines , we report that cells from African straw-colored fruit bats ( Eidolon helvum ) are refractory to EBOV infection . This could be explained by a single amino acid change in the filovirus receptor , NPC1 , which greatly reduces the affinity of EBOV-NPC1 interaction . We found signatures of positive selection in bat NPC1 concentrated at the virus-receptor interface , with the strongest signal at the same residue that controls EBOV infection in Eidolon helvum cells . Our work identifies NPC1 as a genetic determinant of filovirus susceptibility in bats , and suggests that some NPC1 variations reflect host adaptations to reduce filovirus replication and virulence . A single viral mutation afforded escape from receptor control , revealing a pathway for compensatory viral evolution and a potential avenue for expansion of filovirus host range in nature .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Biological factors that influence the host range and spillover of Ebola virus ( EBOV ) and other filoviruses remain enigmatic .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"While filoviruses infect diverse mammalian cell lines ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"we report that cells from African straw-colored fruit bats ( Eidolon helvum ) are refractory to EBOV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"This could be explained by a single amino acid change in the filovirus receptor ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"NPC1 , which greatly reduces the affinity of EBOV-NPC1 interaction .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"We found signatures of positive selection in bat NPC1 concentrated at the virus-receptor interface ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"with the strongest signal at the same residue that controls EBOV infection in Eidolon helvum cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Our work identifies NPC1 as a genetic determinant of filovirus susceptibility in bats ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and suggests that some NPC1 variations reflect host adaptations to reduce filovirus replication and virulence .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"A single viral mutation afforded escape from receptor control ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"revealing a pathway for compensatory viral evolution and a potential avenue for expansion of filovirus host range in nature .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}]}"}]}
{"paper_id": "29db5c5ee576aa04ff7807287ee91b2ca42a5cff", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMethods : Using surface-enhanced laser desorption/ionization ( SELDI ) ProteinChip technology , we profiled and compared serum proteins of 39 patients with earlystage SARS infection and 39 non-SARS patients who were suspected cases during the SARS outbreak period . Proteomic patterns associated with SARS were identified by bioinformatic and biostatistical analyses . Features of interest were then purified and identified by tandem mass spectrometry . Results : Twenty proteomic features were significantly different between the 2 groups . Fifteen were increased in the SARS group , and 5 were decreased . Their concentrations were correlated with 2 or more clinical and/or biochemical variables . Two were correlated with the SARS-CoV viral load . Hierarchical clustering analysis showed that a majority of the SARS patients ( 95 % ) had similar serum proteomic profiles and identified 2 subgroups with poor prognosis . ROC curve analysis identified individual features as potential biomarkers for SARS diagnosis ( areas under ROC curves , 0.733-0.995 ) . ROC curve areas were largest for an N-terminal fragment of complement C3c ␣ chain ( m/z 28 119 ) and an internal fragment of fibrinogen ␣ - E chain ( m/z 5908 ) . Conclusions : Specific proteomic fingerprints in the sera of adult SARS patients could be used to identify SARS cases early during onset with high specificity and sensitivity .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Methods : Using surface-enhanced laser desorption/ionization ( SELDI ) ProteinChip technology ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 1}, {\"segment_text\": \"we profiled and compared serum proteins of 39 patients with earlystage SARS infection and 39 non-SARS patients who were suspected cases during the SARS outbreak period .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"Proteomic patterns associated with SARS were identified by bioinformatic and biostatistical analyses .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Features of interest were then purified and identified by tandem mass spectrometry .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Results : Twenty proteomic features were significantly different between the 2 groups .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Fifteen were increased in the SARS group , and 5 were decreased .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Their concentrations were correlated with 2 or more clinical and/or biochemical variables .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Two were correlated with the SARS-CoV viral load .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Hierarchical clustering analysis showed that a majority of the SARS patients ( 95 % ) had similar serum proteomic profiles and identified 2 subgroups with poor prognosis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"ROC curve analysis identified individual features as potential biomarkers for SARS diagnosis ( areas under ROC curves , 0.733-0.995 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"ROC curve areas were largest for an N-terminal fragment of complement C3c ␣ chain ( m/z 28 119 ) and an internal fragment of fibrinogen ␣ - E chain ( m/z 5908 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Conclusions : Specific proteomic fingerprints in the sera of adult SARS patients could be used to identify SARS cases early during onset with high specificity and sensitivity .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "e04029afe3419cb5033feaa3f911d63028eb8060", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCells expressing the spike ( S ) glycoprotein of the neurotropic JHM strain ( JHMV ) of mouse hepatitis virus ( MHV ) are susceptible to lysis by B cells derived from naïve mice , including B cells from perforin-deficient mice . Cytolysis requires interaction of the virus receptor and the viral S glycoprotein , is independent of other viral-induced components , and is not a unique property of B cells . Neutralizing anti-S-protein monoclonal antibodies ( mAb ) and a mAb specific for the viral receptor inhibit lysis . However , cells infected with an MHV strain unable to induce cell-cell fusion are resistant to lysis and lysis of JHMV-infected cells is inhibited by an anti-S-protein nonneutralizing mAb which prevents S-protein-mediated cell fusion . These data suggest that B cells may function as antibody-independent innate immune response during JHMV infection in vivo .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Cells expressing the spike ( S ) glycoprotein of the neurotropic JHM strain ( JHMV ) of mouse hepatitis virus ( MHV ) are susceptible to lysis by B cells derived from naïve mice ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"including B cells from perforin-deficient mice .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Cytolysis requires interaction of the virus receptor and the viral S glycoprotein ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"is independent of other viral-induced components ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"and is not a unique property of B cells .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Neutralizing anti-S-protein monoclonal antibodies ( mAb ) and a mAb specific for the viral receptor inhibit lysis .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"However , cells infected with an MHV strain unable to induce cell-cell fusion are resistant to lysis and lysis of JHMV-infected cells is inhibited by an anti-S-protein nonneutralizing mAb which prevents S-protein-mediated cell fusion .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"These data suggest that B cells may function as antibody-independent innate immune response during JHMV infection in vivo .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}]}"}]}
{"paper_id": "d508ee56bf2773ed13b19b85295c8e8709781bb7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Extraordinary infection control measures limited access to medical care in the Greater Toronto Area during the 2003 Severe Acute Respiratory Syndrome ( SARS ) outbreak . The objective of this study was to determine if the period of these infection control measures was associated with changes in overall population mortality due to causes other than SARS . Methods : Observational study of death registry data , using Poisson regression and interrupted time-series analysis to examine all-cause mortality rates ( excluding deaths due to SARS ) before , during , and after the SARS outbreak . The population of Ontario was grouped into the Greater Toronto Area ( N = 2.9 million ) and the rest of Ontario ( N = 9.3 million ) based upon the level of restrictions on delivery of clinical services during the SARS outbreak . : There was no significant change in mortality in the Greater Toronto Area before , during , and after the period of the SARS outbreak in 2003 compared to the corresponding time periods in 2002 and 2001 . The rate ratio for all-cause mortality during the SARS outbreak was 0.99 ( 95 % Confidence Interval ( CI ) 0.93-1.06 ) compared to 2002 and 0.96 ( 95 % CI 0.90-1.03 ) compared to 2001 . An interrupted time series analysis found no significant change in mortality rates in the Greater Toronto Area associated with the period of the SARS outbreak . Conclusion : Limitations on access to medical services during the 2003 SARS outbreak in Toronto had no observable impact on short-term population mortality . Effects on morbidity and long-term mortality were not assessed . Efforts to contain future infectious disease outbreaks due to influenza or other agents must consider effects on access to essential health care services .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Extraordinary infection control measures limited access to medical care in the Greater Toronto Area during the 2003 Severe Acute Respiratory Syndrome ( SARS ) outbreak .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The objective of this study was to determine if the period of these infection control measures was associated with changes in overall population mortality due to causes other than SARS .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"Methods : Observational study of death registry data ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"using Poisson regression and interrupted time-series analysis to examine all-cause mortality rates ( excluding deaths due to SARS ) before ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"during , and after the SARS outbreak .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"The population of Ontario was grouped into the Greater Toronto Area ( N = 2.9 million ) and the rest of Ontario ( N = 9.3 million ) based upon the level of restrictions on delivery of clinical services during the SARS outbreak .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \": There was no significant change in mortality in the Greater Toronto Area before ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"during , and after the period of the SARS outbreak in 2003 compared to the corresponding time periods in 2002 and 2001 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"The rate ratio for all-cause mortality during the SARS outbreak was 0.99 ( 95 % Confidence Interval ( CI ) 0.93-1.06 ) compared to 2002 and 0.96 ( 95 % CI 0.90-1.03 ) compared to 2001 .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"An interrupted time series analysis found no significant change in mortality rates in the Greater Toronto Area associated with the period of the SARS outbreak .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Conclusion : Limitations on access to medical services during the 2003 SARS outbreak in Toronto had no observable impact on short-term population mortality .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"Effects on morbidity and long-term mortality were not assessed .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"Efforts to contain future infectious disease outbreaks due to influenza or other agents must consider effects on access to essential health care services .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}]}"}]}
{"paper_id": "87c6c45d9946889a9a3551b31adff4c32c6c237e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nA SARS-CoV lacking the full-length E gene ( SARS-CoV-ΔE ) was attenuated and an effective vaccine . Here , we show that this mutant virus regained fitness after serial passages in cell culture or in vivo , resulting in the partial duplication of the membrane gene or in the insertion of a new sequence in gene 8a , respectively . The chimeric proteins generated in cell culture increased virus fitness in vitro but remained attenuated in mice . In contrast , during SARS-CoV-ΔE passage in mice , the virus incorporated a mutated variant of 8a protein , resulting in reversion to a virulent phenotype . When the full-length E protein was deleted or its PDZ-binding motif ( PBM ) was mutated , the revertant viruses either incorporated a novel chimeric protein with a PBM or restored the sequence of the PBM on the E protein , respectively . Similarly , after passage in mice , SARS-CoV-ΔE protein 8a mutated , to now encode a PBM , and also regained virulence . These data indicated that the virus requires a PBM on a transmembrane protein to compensate for removal of this motif from the E protein . To increase the genetic stability of the vaccine candidate , we introduced small attenuating deletions in E gene that did not affect the endogenous PBM , preventing the incorporation of novel chimeric proteins in the virus genome . In addition , to increase vaccine biosafety , we introduced additional attenuating mutations into the nsp1 protein . Deletions in the carboxyterminal region of nsp1 protein led to higher host interferon responses and virus attenuation . Recombinant viruses including attenuating mutations in E and nsp1 genes maintained their attenuation after passage in vitro and in vivo . Further , these viruses fully protected mice against challenge with the lethal parental virus , and are therefore safe and stable vaccine candidates for protection against SARS-CoV . PLOS Pathogens |\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"A SARS-CoV lacking the full-length E gene ( SARS-CoV-ΔE ) was attenuated and an effective vaccine .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Here , we show that this mutant virus regained fitness after serial passages in cell culture or in vivo ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"resulting in the partial duplication of the membrane gene or in the insertion of a new sequence in gene 8a , respectively .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The chimeric proteins generated in cell culture increased virus fitness in vitro but remained attenuated in mice .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"In contrast , during SARS-CoV-ΔE passage in mice ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"the virus incorporated a mutated variant of 8a protein ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"resulting in reversion to a virulent phenotype .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"When the full-length E protein was deleted or its PDZ-binding motif ( PBM ) was mutated ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"the revertant viruses either incorporated a novel chimeric protein with a PBM or restored the sequence of the PBM on the E protein , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Similarly , after passage in mice ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"SARS-CoV-ΔE protein 8a mutated , to now encode a PBM , and also regained virulence .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"These data indicated that the virus requires a PBM on a transmembrane protein to compensate for removal of this motif from the E protein .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"To increase the genetic stability of the vaccine candidate ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"we introduced small attenuating deletions in E gene that did not affect the endogenous PBM ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"preventing the incorporation of novel chimeric proteins in the virus genome .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"In addition , to increase vaccine biosafety ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"we introduced additional attenuating mutations into the nsp1 protein .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Deletions in the carboxyterminal region of nsp1 protein led to higher host interferon responses and virus attenuation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Recombinant viruses including attenuating mutations in E and nsp1 genes maintained their attenuation after passage in vitro and in vivo .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Further , these viruses fully protected mice against challenge with the lethal parental virus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"and are therefore safe and stable vaccine candidates for protection against SARS-CoV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"PLOS Pathogens |\", \"label\": \"finding\", \"decision_reference\": \"other.rule\", \"id\": 22}]}"}]}
{"paper_id": "e52b14466f05891d49a5ebcdb53b4381f82a0b36", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Cystic fibrosis is a degenerative disease characterized by progressive epithelial secretory gland dysfunction associated with repeated respiratory infections . Bacterial infections are very frequent in children with cystic fibrosis , but because rapid Methods : for screening for the wide variety of potentially involved viruses were unavailable until recently , the frequency of viral presence is unknown . Multiplex PCR enables screening for many viruses involved in respiratory infections . Objectives : This study aimed to evaluate the frequency of viruses and bacteria in respiratory specimens from children with cystic fibrosis and to clarify the incidence and characteristics ( seasonality and age of patients ) of different viruses detected in children with cystic fibrosis . Study design : In this 2-year prospective study , we obtained paired nasopharyngeal-swab and sputum specimens from children with cystic fibrosis during clinical respiratory examinations separated by at least 14 days . We analyzed viruses in nasopharyngeal-swab specimens with multiplex PCR and bacteria in sputum with standard methods . Results : We analyzed 368 paired specimens from 33 children . We detected viruses in 154 ( 41.8 % ) and bacteria in 132 ( 35.9 % ) . Bacteria were commoner in spring and summer ; viruses were commoner in autumn and winter . In every season , Staphylococcus aureus was the commonest bacteria and rhinovirus was the commonest virus . Nearly all infections with Haemophilus influenzae occurred in autumn and winter . Viruses were more prevalent in children < 5 years old , and bacteria were more prevalent in children ≥ 12 years old . Conclusions : Multiplex PCR screening for respiratory viruses is feasible in children with cystic fibrosis ; the clinical implications of screening warrant further study .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Cystic fibrosis is a degenerative disease characterized by progressive epithelial secretory gland dysfunction associated with repeated respiratory infections .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Bacterial infections are very frequent in children with cystic fibrosis ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"but because rapid Methods : for screening for the wide variety of potentially involved viruses were unavailable until recently ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"the frequency of viral presence is unknown .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Multiplex PCR enables screening for many viruses involved in respiratory infections .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Objectives : This study aimed to evaluate the frequency of viruses and bacteria in respiratory specimens from children with cystic fibrosis and to clarify the incidence and characteristics ( seasonality and age of patients ) of different viruses detected in children with cystic fibrosis .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"Study design : In this 2-year prospective study ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"we obtained paired nasopharyngeal-swab and sputum specimens from children with cystic fibrosis during clinical respiratory examinations separated by at least 14 days .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"We analyzed viruses in nasopharyngeal-swab specimens with multiplex PCR and bacteria in sputum with standard methods .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Results : We analyzed 368 paired specimens from 33 children .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"We detected viruses in 154 ( 41.8 % ) and bacteria in 132 ( 35.9 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"Bacteria were commoner in spring and summer ; viruses were commoner in autumn and winter .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"In every season , Staphylococcus aureus was the commonest bacteria and rhinovirus was the commonest virus .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"Nearly all infections with Haemophilus influenzae occurred in autumn and winter .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"Viruses were more prevalent in children < 5 years old ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"and bacteria were more prevalent in children ≥ 12 years old .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"Conclusions : Multiplex PCR screening for respiratory viruses is feasible in children with cystic fibrosis ; the clinical implications of screening warrant further study .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "82b043ec316b0bfb8350d65b09f6028d4ea9e564", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nStructured RNA elements may control virus replication , transcription and translation , and their distinct features are being exploited by novel antiviral strategies . Viral RNA elements continue to be discovered using combinations of experimental and computational analyses . However , the wealth of sequence data , notably from deep viral RNA sequencing , viromes , and metagenomes , necessitates computational approaches being used as an essential discovery tool . In this review , we describe practical approaches being used to discover functional RNA elements in viral genomes . In addition to success stories in new and emerging viruses , these approaches have revealed some surprising new features of well-studied viruses e.g. , human immunodeficiency virus , hepatitis C virus , influenza , and dengue viruses . Some notable discoveries were facilitated by new comparative analyses of diverse viral genome alignments . Importantly , comparative approaches for finding RNA elements embedded in coding and non-coding regions differ . With the exponential growth of computer power we have progressed from stem-loop prediction on single sequences to cutting edge 3D prediction , and from command line to user friendly web interfaces . Despite these advances , many powerful , user friendly prediction tools and resources are underutilized by the virology community .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Structured RNA elements may control virus replication ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"transcription and translation , and their distinct features are being exploited by novel antiviral strategies .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Viral RNA elements continue to be discovered using combinations of experimental and computational analyses .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"However , the wealth of sequence data ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"notably from deep viral RNA sequencing ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"viromes , and metagenomes , necessitates computational approaches being used as an essential discovery tool .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"In this review , we describe practical approaches being used to discover functional RNA elements in viral genomes .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"In addition to success stories in new and emerging viruses ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"these approaches have revealed some surprising new features of well-studied viruses e.g. ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"human immunodeficiency virus , hepatitis C virus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"influenza , and dengue viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Some notable discoveries were facilitated by new comparative analyses of diverse viral genome alignments .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Importantly , comparative approaches for finding RNA elements embedded in coding and non-coding regions differ .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"With the exponential growth of computer power we have progressed from stem-loop prediction on single sequences to cutting edge 3D prediction ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"and from command line to user friendly web interfaces .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Despite these advances , many powerful ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"user friendly prediction tools and resources are underutilized by the virology community .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "da4dc24b9006d09f751909a00724f771f6577501", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe sudden death of three calves , one diarrheic calf , and one aborted fetus from four farms in southern Brazil was investigated . Two Histophilus somni-associated syndromes were identified : systemic histophilosis ( n = 4 ) and abortion ( n = 1 ) . The principal pathological findings included vasculitis , meningoencephalitis with thrombosis , necrotizing myocarditis , renal infarctions , hepatic abscesses , and bronchopneumonia . PCR assays were used to amplify specific amplicons of the ovine herpesvirus 2 , bovine herpesvirus 1 and − 5 , Listeria monocytogenes , H. somni , and pestivirus ; bovine group A rotavirus ( BoRV-A ) and bovine coronavirus ( BCoV ) were investigated in calves with diarrhea . H. somni DNA was amplified in tissues from all calves and the brain of the aborted fetus with pathological alterations consistent with histophilosis . All other PCR assays were negative ; BoRV-A and BCoV were not identified . These findings confirm the participation of H. somni in the pathological alterations observed in this study and represent the first description of histophilosis in cattle from Brazil .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The sudden death of three calves ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"one diarrheic calf , and one aborted fetus from four farms in southern Brazil was investigated .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Two Histophilus somni-associated syndromes were identified : systemic histophilosis ( n = 4 ) and abortion ( n = 1 ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"The principal pathological findings included vasculitis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 4}, {\"segment_text\": \"meningoencephalitis with thrombosis , necrotizing myocarditis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"renal infarctions , hepatic abscesses , and bronchopneumonia .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"PCR assays were used to amplify specific amplicons of the ovine herpesvirus 2 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"bovine herpesvirus 1 and − 5 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Listeria monocytogenes , H. somni ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"and pestivirus ; bovine group A rotavirus ( BoRV-A ) and bovine coronavirus ( BCoV ) were investigated in calves with diarrhea .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"H. somni DNA was amplified in tissues from all calves and the brain of the aborted fetus with pathological alterations consistent with histophilosis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"All other PCR assays were negative ; BoRV-A and BCoV were not identified .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"These findings confirm the participation of H. somni in the pathological alterations observed in this study and represent the first description of histophilosis in cattle from Brazil .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "3dd2a8d91d8e2c7903683b82193424528a642067", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe advancement in technology is likely to tame several life forms present on earth . Microorganisms are posing a big challenge due to diffi culties encountered to control the diseases caused by them . Working with deadly disease-causing microorganisms for their characterization , diagnostics or therapeutics and vaccine development purposes are posing increasingly potential biosafety problems for laboratory workers . Thus , an appropriate biosafe working environment may protect workers from laboratoryinduced infections . Biotechnology has the ability to solve the upcoming problems of the world 's increasing population . However , there is often reluctance among the public to accept and support biotechnological products in medicine , industry , or agriculture . There are many safety and ethical issues raised for GM crops and human cloning . Raising transgenic animals and plants has fueled ethical concerns , and the scientists have faced a lot of resistance where genetically modifi ed crop plants or reproductive cloning research of human beings is involved . Thus , biosafety and bioethics are continuously being expanded to combine the rationale of ever-increasing scientifi c knowledge in biotechnology that is often in confl ict with the long-standing social and moral value system of our society .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The advancement in technology is likely to tame several life forms present on earth .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Microorganisms are posing a big challenge due to diffi culties encountered to control the diseases caused by them .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Working with deadly disease-causing microorganisms for their characterization ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"diagnostics or therapeutics and vaccine development purposes are posing increasingly potential biosafety problems for laboratory workers .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Thus , an appropriate biosafe working environment may protect workers from laboratoryinduced infections .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Biotechnology has the ability to solve the upcoming problems of the world 's increasing population .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"However , there is often reluctance among the public to accept and support biotechnological products in medicine , industry , or agriculture .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"There are many safety and ethical issues raised for GM crops and human cloning .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"Raising transgenic animals and plants has fueled ethical concerns ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"and the scientists have faced a lot of resistance where genetically modifi ed crop plants or reproductive cloning research of human beings is involved .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"Thus , biosafety and bioethics are continuously being expanded to combine the rationale of ever-increasing scientifi c knowledge in biotechnology that is often in confl ict with the long-standing social and moral value system of our society .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}]}"}]}
{"paper_id": "e725656b0cdd0f7e78279187e0c251cf8683f1e5", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nHepatitis C virus ( HCV ) infection is a major cause of chronic liver disease and has become a global health threat . No HCV vaccine is currently available and treatment with antiviral therapy is associated with adverse side effects . Moreover , there is no preventive therapy for recurrent hepatitis C post liver transplantation . The NS3 serine protease is necessary for HCV replication and represents a prime target for developing anti HCV therapies . Recently we described a therapeutic approach for eradication of HCV infected cells that is based on protein delivery of two NS3 protease-activatable recombinant toxins we named `` zymoxins '' . These toxins were inactivated by fusion to rationally designed inhibitory peptides via NS3-cleavable linkers . Once delivered to cells where NS3 protease is present , the inhibitory peptide is removed resulting in re-activation of cytotoxic activity . The zymoxins we described suffered from two limitations : they required high levels of protease for activation and had basal activities in the un-activated form that resulted in a narrow potential therapeutic window . Here , we present a solution that overcame the major limitations of the `` first generation zymoxins '' by converting MazF ribonuclease , the toxic component of the E. coli chromosomal MazEF toxin-antitoxin system , into an NS3-activated zymoxin that is introduced to cells by means of gene delivery . We constructed an expression cassette that encodes for a single polypeptide that incorporates both the toxin and a fragment of its potent natural antidote , MazE , linked via an NS3-cleavable linker . While covalently paired to its inhibitor , the ribonuclease is well tolerated when expressed in naïve , healthy cells . In contrast , activating proteolysis that is induced by even low levels of NS3 , results in an eradication of NS3 expressing model cells and HCV infected cells . Zymoxins may thus become a valuable tool in eradicating cells infected by intracellular pathogens that express intracellular proteases .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Hepatitis C virus ( HCV ) infection is a major cause of chronic liver disease and has become a global health threat .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"No HCV vaccine is currently available and treatment with antiviral therapy is associated with adverse side effects .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Moreover , there is no preventive therapy for recurrent hepatitis C post liver transplantation .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"The NS3 serine protease is necessary for HCV replication and represents a prime target for developing anti HCV therapies .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Recently we described a therapeutic approach for eradication of HCV infected cells that is based on protein delivery of two NS3 protease-activatable recombinant toxins we named `` zymoxins '' .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"These toxins were inactivated by fusion to rationally designed inhibitory peptides via NS3-cleavable linkers .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"Once delivered to cells where NS3 protease is present ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"the inhibitory peptide is removed resulting in re-activation of cytotoxic activity .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"The zymoxins we described suffered from two limitations : they required high levels of protease for activation and had basal activities in the un-activated form that resulted in a narrow potential therapeutic window .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"Here , we present a solution that overcame the major limitations of the `` first generation zymoxins '' by converting MazF ribonuclease ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"the toxic component of the E. coli chromosomal MazEF toxin-antitoxin system ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"into an NS3-activated zymoxin that is introduced to cells by means of gene delivery .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"We constructed an expression cassette that encodes for a single polypeptide that incorporates both the toxin and a fragment of its potent natural antidote ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"MazE , linked via an NS3-cleavable linker .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"While covalently paired to its inhibitor ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"the ribonuclease is well tolerated when expressed in naïve , healthy cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"In contrast , activating proteolysis that is induced by even low levels of NS3 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"results in an eradication of NS3 expressing model cells and HCV infected cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Zymoxins may thus become a valuable tool in eradicating cells infected by intracellular pathogens that express intracellular proteases .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}]}"}]}
{"paper_id": "78105213b5413694357b77b5f55f6750db8250fa", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : The 2003 outbreak of severe acute respiratory syndrome ( SARS ) infected over 8000 people and killed 774 . Transmission of SARS occurred through direct and indirect contact and large droplet nuclei . The World Health Organization recommended the use of household disinfectants , which have not been previously tested against SARS coronavirus ( SARS-CoV ) , to disinfect potentially contaminated environmental surfaces . There is a need for a surrogate test system given the limited availability of the SARS-CoV for testing and biosafety requirements necessary to safely handle it . In this study , the antiviral activity of standard household products was assayed against murine hepatitis virus ( MHV ) , as a potential surrogate for SARS-CoV . Methods : A surface test method , which involves drying an amount of virus on a surface and then applying the product for a specific contact time , was used to determine the virucidal activity . The virus titers and log reductions were determined by the Reed and Muench tissue culture infective dose ( TCID ) 50 end point method . Results : When tested as directed , common household disinfectants or antiseptics , containing either 0.050 % of triclosan , 0.12 % of PCMX , 0.21 % of sodium hypochlorite , 0.23 % of pine oil , or 0.10 % of a quaternary compound with 79 % of ethanol , demonstrated a 3-log reduction or better against MHV without any virus recovered in a 30-second contact time . Conclusion : Common household disinfectants and antiseptics were effective at inactivating MHV , a possible surrogate for SARS-CoV , from surfaces when used as directed . In an outbreak caused by novel agents , it is important to know the effectiveness of disinfectants and antiseptics to prevent or reduce the possibility of human-to-human transmission via surfaces . NOTE . Calculations were performed using the Reed and Muench TCID 50 end point expressed as log 10 TCID 50 / mL . 8,9 CPE , cytopathogenic effect ; MHV , murine hepatitis virus ; Rep , replicate ; PCMX , parachlorometaxylenol . * Test procedure performed not using sephadex columns but still met the 3-log reduction success criteria .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : The 2003 outbreak of severe acute respiratory syndrome ( SARS ) infected over 8000 people and killed 774 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Transmission of SARS occurred through direct and indirect contact and large droplet nuclei .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The World Health Organization recommended the use of household disinfectants ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"which have not been previously tested against SARS coronavirus ( SARS-CoV ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"to disinfect potentially contaminated environmental surfaces .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"There is a need for a surrogate test system given the limited availability of the SARS-CoV for testing and biosafety requirements necessary to safely handle it .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"In this study , the antiviral activity of standard household products was assayed against murine hepatitis virus ( MHV ) ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"as a potential surrogate for SARS-CoV .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"Methods : A surface test method ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"which involves drying an amount of virus on a surface and then applying the product for a specific contact time ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"was used to determine the virucidal activity .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"The virus titers and log reductions were determined by the Reed and Muench tissue culture infective dose ( TCID ) 50 end point method .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"Results : When tested as directed ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"common household disinfectants or antiseptics ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"containing either 0.050 % of triclosan ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"0.12 % of PCMX , 0.21 % of sodium hypochlorite ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"0.23 % of pine oil ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"or 0.10 % of a quaternary compound with 79 % of ethanol ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"demonstrated a 3-log reduction or better against MHV without any virus recovered in a 30-second contact time .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"Conclusion : Common household disinfectants and antiseptics were effective at inactivating MHV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}, {\"segment_text\": \"a possible surrogate for SARS-CoV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}, {\"segment_text\": \"from surfaces when used as directed .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 22}, {\"segment_text\": \"In an outbreak caused by novel agents ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 23}, {\"segment_text\": \"it is important to know the effectiveness of disinfectants and antiseptics to prevent or reduce the possibility of human-to-human transmission via surfaces .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 24}, {\"segment_text\": \"NOTE .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 25}, {\"segment_text\": \"Calculations were performed using the Reed and Muench TCID 50 end point expressed as log 10 TCID 50 / mL .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 26}, {\"segment_text\": \"8,9 CPE , cytopathogenic effect ; MHV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 27}, {\"segment_text\": \"murine hepatitis virus ; Rep ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 28}, {\"segment_text\": \"replicate ; PCMX , parachlorometaxylenol .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 29}, {\"segment_text\": \"* Test procedure performed not using sephadex columns but still met the 3-log reduction success criteria .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 30}]}"}]}
{"paper_id": "e1d7e834b98f69880f50a402eb627336ed79f1e6", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSevere acute respiratory syndrome ( SARS ) is caused by a novel coronavirus ( SARS-CoV ) strain and is clinically similar to many other acute respiratory infections ( 1 , 2 ) . Its symptoms include high fever , chills , rigors , dyspnea , nonproductive cough , myalgias ,\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Severe acute respiratory syndrome ( SARS ) is caused by a novel coronavirus ( SARS-CoV ) strain and is clinically similar to many other acute respiratory infections ( 1 , 2 ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Its symptoms include high fever ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"chills , rigors , dyspnea , nonproductive cough , myalgias ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}]}"}]}
{"paper_id": "461376ba087980663244b082070af5039fea2249", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCryptococcus gattii is a pathogenic environmental yeast that is considered to be emerging in different areas of the world including the Mediterranean Basin . Exposure to infection might be more likely in animals than in human beings , given their closer relationship with the natural habitat of the yeast , vegetation and soil . Thus , animals , and especially pets , can act as indicators of the presence of this yeast in a determined area . Domestic ferrets ( Mustela putorius furo ) have become common pets in the past 10-20 years . Their natural behavior of sniffing around and going inside narrow spaces makes them prone to contact with decaying organic matter and soil , the substrate for Cryptococcus species . This study describes two cases of cryptococcosis in ferrets in the Iberian Peninsula and Balearic Islands and documents a relationship of ferret cryptococcosis with environmental isolates in the same locations . Here , we emphasize the importance of how an adequate identification and environmental search of the yeast leads to a better understanding of the epidemiology of cryptococcosis and suggests ferrets may act as sentinels for this fungal disease .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Cryptococcus gattii is a pathogenic environmental yeast that is considered to be emerging in different areas of the world including the Mediterranean Basin .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Exposure to infection might be more likely in animals than in human beings ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"given their closer relationship with the natural habitat of the yeast , vegetation and soil .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Thus , animals , and especially pets ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"can act as indicators of the presence of this yeast in a determined area .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Domestic ferrets ( Mustela putorius furo ) have become common pets in the past 10-20 years .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Their natural behavior of sniffing around and going inside narrow spaces makes them prone to contact with decaying organic matter and soil ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"the substrate for Cryptococcus species .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"This study describes two cases of cryptococcosis in ferrets in the Iberian Peninsula and Balearic Islands and documents a relationship of ferret cryptococcosis with environmental isolates in the same locations .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Here , we emphasize the importance of how an adequate identification and environmental search of the yeast leads to a better understanding of the epidemiology of cryptococcosis and suggests ferrets may act as sentinels for this fungal disease .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "39f8fc7fe362f52cdef1d3b637989901fa41f8fc", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMiddle East respiratory syndrome coronavirus ( MERS-CoV ) has infected at least 2040 patients and caused 712 deaths since its first appearance in 2012 , yet neither pathogen-specific therapeutics nor approved vaccines are available . To address this need , we are developing a subunit recombinant protein vaccine comprising residues 377-588 of the MERS-CoV spike protein receptor-binding domain ( RBD ) , which , when formulated with the AddaVax adjuvant , it induces a significant neutralizing antibody response and protection against MERS-CoV challenge in vaccinated animals . To prepare for the manufacture and first-in-human testing of the vaccine , we have developed a process to stably produce the recombinant MERS S377-588 protein in Chinese hamster ovary ( CHO ) cells . To accomplish this , we transfected an adherent dihydrofolate reductase-deficient CHO cell line ( adCHO ) with a plasmid encoding S377-588 fused with the human IgG Fc fragment ( S377-588-Fc ) . We then demonstrated the interleukin-2 signal peptide-directed secretion of the recombinant protein into extracellular milieu . Using a gradually increasing methotrexate ( MTX ) concentration to 5 lM , we increased protein yield by a factor of 40 . The adCHO-expressed S377-588-Fc recombinant protein demonstrated functionality and binding specificity identical to those of the protein from transiently transfected HEK293T cells . In addition , hCD26 / dipeptidyl peptidase-4 ( DPP4 ) transgenic mice vaccinated with AddaVax-adjuvanted S377-588-Fc could produce neutralizing antibodies against MERS-CoV and survived for at least 21 days after challenge with live MERS-CoV with no evidence of immunological toxicity or eosinophilic immune enhancement . To prepare for large scale-manufacture of the vaccine antigen , we have further developed a high-yield monoclonal suspension CHO cell line .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Middle East respiratory syndrome coronavirus ( MERS-CoV ) has infected at least 2040 patients and caused 712 deaths since its first appearance in 2012 ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"yet neither pathogen-specific therapeutics nor approved vaccines are available .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"To address this need , we are developing a subunit recombinant protein vaccine comprising residues 377-588 of the MERS-CoV spike protein receptor-binding domain ( RBD ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"which , when formulated with the AddaVax adjuvant ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"it induces a significant neutralizing antibody response and protection against MERS-CoV challenge in vaccinated animals .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"To prepare for the manufacture and first-in-human testing of the vaccine ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"we have developed a process to stably produce the recombinant MERS S377-588 protein in Chinese hamster ovary ( CHO ) cells .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"To accomplish this , we transfected an adherent dihydrofolate reductase-deficient CHO cell line ( adCHO ) with a plasmid encoding S377-588 fused with the human IgG Fc fragment ( S377-588-Fc ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"We then demonstrated the interleukin-2 signal peptide-directed secretion of the recombinant protein into extracellular milieu .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Using a gradually increasing methotrexate ( MTX ) concentration to 5 lM ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"we increased protein yield by a factor of 40 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"The adCHO-expressed S377-588-Fc recombinant protein demonstrated functionality and binding specificity identical to those of the protein from transiently transfected HEK293T cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"In addition , hCD26 / dipeptidyl peptidase-4 ( DPP4 ) transgenic mice vaccinated with AddaVax-adjuvanted S377-588-Fc could produce neutralizing antibodies against MERS-CoV and survived for at least 21 days after challenge with live MERS-CoV with no evidence of immunological toxicity or eosinophilic immune enhancement .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"To prepare for large scale-manufacture of the vaccine antigen ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"we have further developed a high-yield monoclonal suspension CHO cell line .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}]}"}]}
{"paper_id": "1e2493a8e26be4ff934b96dedc32dc7cf5728370", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Porcine epidemic diarrhea virus ( PEDV ) is a highly contagious enteric pathogen of swine . The spike glycoprotein ( S ) of PEDV is the major immunogenic determinant that plays a pivotal role in the induction of neutralizing antibodies against PEDV , which therefore is an ideal target for the development of subunit vaccine . In an attempt to develop a subunit vaccine for PEDV , we cloned two different fragments of S protein and expressed as glutathione S-transferase ( GST ) - tagged fusion proteins , namely rGST-COE and rGST-S1D , in E.coli . However , the expression of these recombinant protein antigens using a variety of expression vectors , strains , and induction conditions invariably resulted in inclusion bodies . To achieve the soluble expression of recombinant proteins , several chaperone co-expression systems were tested in this study . Results : We firstly tested various chaperone co-expression systems and found that co-expression of trigger factor ( TF ) with recombinant proteins at 15 °C was most useful in soluble production of rGST-COE and rGST-S1D compared to GroEL-ES and DnaK-DnaJ-GrpE/GroEL-ES systems . The soluble rGST-COE and rGST-S1D were purified using glutathione Sepharose 4B with a yield of 7.5 mg/l and 5 mg/l , respectively . Purified proteins were detected by western blot using mouse anti-GST mAb and pig anti-PEDV immune sera . In an indirect ELISA , purified proteins showed immune reactivity with pig anti-PEDV immune sera . Finally , immunization of mice with 10 μg of purified proteins elicited highly potent serum IgG and serum neutralizing antibody titers . Conclusions : In this study , soluble production of recombinant spike protein of PEDV , rGST-COE and rGST-S1D , were achieved by using TF chaperone co-expression system . Our results suggest that soluble rGST-COE and rGST-S1D produced by co-expressing chaperones may have the potential to be used as subunit vaccine antigens .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Porcine epidemic diarrhea virus ( PEDV ) is a highly contagious enteric pathogen of swine .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The spike glycoprotein ( S ) of PEDV is the major immunogenic determinant that plays a pivotal role in the induction of neutralizing antibodies against PEDV ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"which therefore is an ideal target for the development of subunit vaccine .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"In an attempt to develop a subunit vaccine for PEDV ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"we cloned two different fragments of S protein and expressed as glutathione S-transferase ( GST ) - tagged fusion proteins ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"namely rGST-COE and rGST-S1D , in E.coli .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"However , the expression of these recombinant protein antigens using a variety of expression vectors ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"strains , and induction conditions invariably resulted in inclusion bodies .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"To achieve the soluble expression of recombinant proteins ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"several chaperone co-expression systems were tested in this study .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Results : We firstly tested various chaperone co-expression systems and found that co-expression of trigger factor ( TF ) with recombinant proteins at 15 °C was most useful in soluble production of rGST-COE and rGST-S1D compared to GroEL-ES and DnaK-DnaJ-GrpE/GroEL-ES systems .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"The soluble rGST-COE and rGST-S1D were purified using glutathione Sepharose 4B with a yield of 7.5 mg/l and 5 mg/l , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Purified proteins were detected by western blot using mouse anti-GST mAb and pig anti-PEDV immune sera .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"In an indirect ELISA , purified proteins showed immune reactivity with pig anti-PEDV immune sera .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Finally , immunization of mice with 10 μg of purified proteins elicited highly potent serum IgG and serum neutralizing antibody titers .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Conclusions : In this study ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"soluble production of recombinant spike protein of PEDV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"rGST-COE and rGST-S1D , were achieved by using TF chaperone co-expression system .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Our results suggest that soluble rGST-COE and rGST-S1D produced by co-expressing chaperones may have the potential to be used as subunit vaccine antigens .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}]}"}]}
{"paper_id": "8da5d4c7d3f991b1538e839ed944dcd2167112d0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRenin angiotensin system ( RAS ) is known to play a key role in several diseases such as diabetes , and renal and cardiovascular pathologies . Its blockade has been demonstrated to delay chronic kidney disease progression and cardiovascular damage in diabetic patients . In this sense , since local RAS has been described , the aim of this study is to characterize angiotensin converting enzyme ( ACE ) and ACE2 activities , as well as protein expression , in several tissues of the non-obese diabetic ( NOD ) mice model . After 21 or 40 days of diabetes onset , mouse serums and tissues were analyzed for ACE and ACE2 enzyme activities and protein expression . ACE and ACE2 enzyme activities were detected in different tissues . Their expressions vary depending on the studied tissue . Thus , whereas ACE activity was highly expressed in lungs , ACE2 activity was highly expressed in pancreas among the studied tissues . Interestingly , we also observed that diabetes up-regulates ACE mainly in serum , lung , heart , and liver , and ACE2 mainly in serum , liver , and pancreas . In conclusion , we found a marked serum and pulmonary alteration in ACE activity of diabetic mice , suggesting a common regulation . The increase of ACE2 activity within the circulation in diabetic mice may be ascribed to a compensatory mechanism of RAS .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Renin angiotensin system ( RAS ) is known to play a key role in several diseases such as diabetes ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"and renal and cardiovascular pathologies .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Its blockade has been demonstrated to delay chronic kidney disease progression and cardiovascular damage in diabetic patients .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"In this sense , since local RAS has been described ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"the aim of this study is to characterize angiotensin converting enzyme ( ACE ) and ACE2 activities ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"as well as protein expression ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"in several tissues of the non-obese diabetic ( NOD ) mice model .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"After 21 or 40 days of diabetes onset ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"mouse serums and tissues were analyzed for ACE and ACE2 enzyme activities and protein expression .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"ACE and ACE2 enzyme activities were detected in different tissues .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Their expressions vary depending on the studied tissue .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Thus , whereas ACE activity was highly expressed in lungs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"ACE2 activity was highly expressed in pancreas among the studied tissues .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Interestingly , we also observed that diabetes up-regulates ACE mainly in serum ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"lung , heart , and liver ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"and ACE2 mainly in serum , liver , and pancreas .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"In conclusion , we found a marked serum and pulmonary alteration in ACE activity of diabetic mice , suggesting a common regulation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"The increase of ACE2 activity within the circulation in diabetic mice may be ascribed to a compensatory mechanism of RAS .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "74f823e968a2920c96c87977da7289f5363979da", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe ability of pathogens to escape the host 's immune response is crucial for the establishment of persistent infections and can influence virulence . Recombination has been observed to contribute to this process by generating novel genetic variants . Although distinctive recombination patterns have been described in many viral pathogens , little is known about the influence of biases in the recombination process itself relative to selective forces acting on newly formed recombinants . Understanding these influences is important for determining how recombination contributes to pathogen genome and proteome evolution . Most previous research on recombination-driven protein evolution has focused on relatively simple proteins , usually in the context of directed evolution experiments . Here , we study recombination in the envelope gene of HIV-1 between primary isolates belonging to subtypes that recombine naturally in the HIV/AIDS pandemic . By characterizing the early steps in the generation of recombinants , we provide novel insights into the evolutionary forces that shape recombination patterns within viral populations . Specifically , we show that the combined effects of mechanistic processes that determine the locations of recombination breakpoints across the HIV-1 envelope gene , and purifying selection acting against dysfunctional recombinants , can explain almost the entire distribution of breakpoints found within this gene in nature . These constraints account for the surprising paucity of recombination breakpoints found in infected individuals within this highly variable gene . Thus , the apparent randomness of HIV evolution via recombination may in fact be relatively more predictable than anticipated . In addition , the dominance of purifying selection in localized areas of the HIV genome defines regions where functional constraints on recombinants appear particularly strong , pointing to vulnerable aspects of HIV biology .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The ability of pathogens to escape the host 's immune response is crucial for the establishment of persistent infections and can influence virulence .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Recombination has been observed to contribute to this process by generating novel genetic variants .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Although distinctive recombination patterns have been described in many viral pathogens ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"little is known about the influence of biases in the recombination process itself relative to selective forces acting on newly formed recombinants .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Understanding these influences is important for determining how recombination contributes to pathogen genome and proteome evolution .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Most previous research on recombination-driven protein evolution has focused on relatively simple proteins ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"usually in the context of directed evolution experiments .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"Here , we study recombination in the envelope gene of HIV-1 between primary isolates belonging to subtypes that recombine naturally in the HIV/AIDS pandemic .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"By characterizing the early steps in the generation of recombinants ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"we provide novel insights into the evolutionary forces that shape recombination patterns within viral populations .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Specifically , we show that the combined effects of mechanistic processes that determine the locations of recombination breakpoints across the HIV-1 envelope gene ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and purifying selection acting against dysfunctional recombinants ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"can explain almost the entire distribution of breakpoints found within this gene in nature .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"These constraints account for the surprising paucity of recombination breakpoints found in infected individuals within this highly variable gene .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Thus , the apparent randomness of HIV evolution via recombination may in fact be relatively more predictable than anticipated .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"In addition , the dominance of purifying selection in localized areas of the HIV genome defines regions where functional constraints on recombinants appear particularly strong ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"pointing to vulnerable aspects of HIV biology .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "e1e8903986998f998a4ee66cbbf1c0b05ebf2eb1", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Herpes B virus ( BV ) is a zoonotic disease caused by double-stranded enveloped DNA virus with cercopithecidae as its natural host . The mortality rate of infected people could be up to 70 % with fatal encephalitis and encephalomyelitis . Up to now , there are no effective treatments for BV infection . Among the various proteins encoded by monkey B virus , gD , a conserved structural protein , harbors important application value for serological diagnosis of frequent variations of the monkey B virus . Objectives : This study aimed to expressed the gD protein of BV in Escherichia coli by a recombinant vector , and prepare specific monoclonal antibodies against gD of BV to pave the way for effective and quick diagnosis reagent research . The gD gene of BV was optimized by OptimWiz to improve codon usage bias and synthesis , and the recombinant plasmid , pET32a/gD , was constructed and expressed in E. coli Rosetta ( DE3 ) . The expressed fusion protein , His-gD , was purified and the BALB/c mice were immunized by this protein . Spleen cells from the immunized mice and SP2/0 myeloma cells were fused together , and the monoclonal cell strains were obtained by indirect enzyme-linked immunosorbent assay ( ELISA ) screening , followed by preparation of monoclonal antibody ascetic fluid . The optimized gD protein was highly expressed in E. coli and successfully purified . Five monoclonal antibodies ( mAbs ) against BV were obtained and named as 4E3 , 3F8 , 3E7 , 1H3 and 4B6 , and with ascetic fluid titers of 2 × 10 6 , 2 × 10 5 , 2 × 10 5 , 2 × 10 3 and 2 × 10 2 , respectively . The 1H3 and 4E3 belonged to the IgG2b subclass , while 3E7 , 3F8 and 4B6 belonged to the IgG1 subclass . The cell lines obtained in this work secreted potent , stable and specific anti-BV mAbs , which were suitable for the development of herpes B virus diagnosis reagents .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Herpes B virus ( BV ) is a zoonotic disease caused by double-stranded enveloped DNA virus with cercopithecidae as its natural host .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The mortality rate of infected people could be up to 70 % with fatal encephalitis and encephalomyelitis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Up to now , there are no effective treatments for BV infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Among the various proteins encoded by monkey B virus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"gD , a conserved structural protein ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"harbors important application value for serological diagnosis of frequent variations of the monkey B virus .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Objectives : This study aimed to expressed the gD protein of BV in Escherichia coli by a recombinant vector ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"and prepare specific monoclonal antibodies against gD of BV to pave the way for effective and quick diagnosis reagent research .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"The gD gene of BV was optimized by OptimWiz to improve codon usage bias and synthesis ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"and the recombinant plasmid , pET32a/gD ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"was constructed and expressed in E. coli Rosetta ( DE3 ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"The expressed fusion protein , His-gD ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"was purified and the BALB/c mice were immunized by this protein .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"Spleen cells from the immunized mice and SP2/0 myeloma cells were fused together ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"and the monoclonal cell strains were obtained by indirect enzyme-linked immunosorbent assay ( ELISA ) screening ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 15}, {\"segment_text\": \"followed by preparation of monoclonal antibody ascetic fluid .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 16}, {\"segment_text\": \"The optimized gD protein was highly expressed in E. coli and successfully purified .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Five monoclonal antibodies ( mAbs ) against BV were obtained and named as 4E3 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"3F8 , 3E7 , 1H3 and 4B6 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"and with ascetic fluid titers of 2 × 10 6 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"2 × 10 5 , 2 × 10 5 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"2 × 10 3 and 2 × 10 2 , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"The 1H3 and 4E3 belonged to the IgG2b subclass ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"while 3E7 , 3F8 and 4B6 belonged to the IgG1 subclass .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}, {\"segment_text\": \"The cell lines obtained in this work secreted potent ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 25}, {\"segment_text\": \"stable and specific anti-BV mAbs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 26}, {\"segment_text\": \"which were suitable for the development of herpes B virus diagnosis reagents .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 27}]}"}]}
{"paper_id": "68b8a4f644c4195bd6a89ea7e70cd45072ea979e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nTo date , 1841 cases of Middle East respiratory syndrome coronavirus ( MERS-CoV ) infection have been reported worldwide , with 652 deaths . We used a publically available case line list to explore the effect of relevant factors , notably underlying comorbidities , on fatal outcome of Middle East respiratory syndrome ( MERS ) cases up to the end of October 2016 . A Bayesian Weibull proportional hazards regression model was used to assess the effect of comorbidity , age , epidemic period and sex on the fatality rate of MERS cases and its variation across countries . The crude fatality rate of MERS cases was 32.1 % ( 95 % credibility interval ( CI ) : 29.9 % , 34.3 % ) . Notably , the incremental change of daily death rate was most prominent during the first week since disease onset with an average increase of 13 % , but then stabilized in the remaining two weeks when it only increased 3 % on average . Neither sex , nor country of infection were found to have a significant impact on fatality rates after taking into account the age and comorbidity status of patients . After adjusting for age , epidemic period , MERS patients with comorbidity had around 4 times the risk for fatal infection than those without ( adjusted hazard ratio of 3.74 ( 95 % CI : 2.57 , 5.67 ) ) .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"To date , 1841 cases of Middle East respiratory syndrome coronavirus ( MERS-CoV ) infection have been reported worldwide , with 652 deaths .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"We used a publically available case line list to explore the effect of relevant factors ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"notably underlying comorbidities , on fatal outcome of Middle East respiratory syndrome ( MERS ) cases up to the end of October 2016 .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"A Bayesian Weibull proportional hazards regression model was used to assess the effect of comorbidity ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"age , epidemic period and sex on the fatality rate of MERS cases and its variation across countries .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"The crude fatality rate of MERS cases was 32.1 % ( 95 % credibility interval ( CI ) : 29.9 % , 34.3 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"Notably , the incremental change of daily death rate was most prominent during the first week since disease onset with an average increase of 13 % ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"but then stabilized in the remaining two weeks when it only increased 3 % on average .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"Neither sex , nor country of infection were found to have a significant impact on fatality rates after taking into account the age and comorbidity status of patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"After adjusting for age , epidemic period ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"MERS patients with comorbidity had around 4 times the risk for fatal infection than those without ( adjusted hazard ratio of 3.74 ( 95 % CI : 2.57 , 5.67 ) ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}]}"}]}
{"paper_id": "e64ca702639685bdb9860a30f29864f2bf01c480", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCoronavirus envelope protein is a small membrane protein and minor component of the virus particles . It plays important roles in virion assembly and morphogenesis , alteration of the membrane permeability of host cells and virus-host cell interaction . Here we review recent progress in characterization of the biochemical properties , membrane topology and functions of the protein .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Coronavirus envelope protein is a small membrane protein and minor component of the virus particles .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"It plays important roles in virion assembly and morphogenesis ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"alteration of the membrane permeability of host cells and virus-host cell interaction .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Here we review recent progress in characterization of the biochemical properties ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"membrane topology and functions of the protein .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}]}"}]}
{"paper_id": "e1dcb7afad633edb713f9933d9daaf4040ce5c01", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPorcine hemagglutinating encephalomyelitis virus ( PHEV ) is a member of the genus betacoronavirus within the family coronaviridae , which invades the central nervous system ( CNS ) via peripheral nervous system and causes encephalomyelitis or vomiting and wasting disease ( VWD ) in sucking piglets . Up to now , although few complete nucleotide sequences of PHEV have been reported , they are not annotated . This study aimed to illuminate genome characterization , phylogenesis and pathogenicity of the PHEV/2008 strain . The full length of the PHEV/2008 strain genome was 30,684 bp , with a G + C content of 37.27 % . The genome included at a minimum of 11 predicted open reading frames ( ORFs ) flanked by 5 ′ and 3 ′ untranslated regions ( UTR ) of 211 and 289 nucleotides . The replicase polyproteins pp1a and pp1ab , which had 4382 and 7094 amino acid residues , respectively , were predicted to be cleaved into 16 subunits by two viral proteinases . Phylogenetic analysis based on the complete genome sequence revealed that PHEV/2008 strain was genetically different from other known PHEV types , which represented a novel genotype ( GI-1 ) . In addition , we found that PHEV/2008 was neurotropic and highly pathogenic to 4-week-old BALB/c mice . Taken together , this is the first detailed annotated , complete genomic sequence of a new genotype PHEV strain in China .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Porcine hemagglutinating encephalomyelitis virus ( PHEV ) is a member of the genus betacoronavirus within the family coronaviridae ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"which invades the central nervous system ( CNS ) via peripheral nervous system and causes encephalomyelitis or vomiting and wasting disease ( VWD ) in sucking piglets .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Up to now , although few complete nucleotide sequences of PHEV have been reported , they are not annotated .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"This study aimed to illuminate genome characterization ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"phylogenesis and pathogenicity of the PHEV/2008 strain .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"The full length of the PHEV/2008 strain genome was 30,684 bp ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"with a G + C content of 37.27 % .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"The genome included at a minimum of 11 predicted open reading frames ( ORFs ) flanked by 5 ′ and 3 ′ untranslated regions ( UTR ) of 211 and 289 nucleotides .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The replicase polyproteins pp1a and pp1ab ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"which had 4382 and 7094 amino acid residues ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"respectively , were predicted to be cleaved into 16 subunits by two viral proteinases .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Phylogenetic analysis based on the complete genome sequence revealed that PHEV/2008 strain was genetically different from other known PHEV types ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"which represented a novel genotype ( GI-1 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"In addition , we found that PHEV/2008 was neurotropic and highly pathogenic to 4-week-old BALB/c mice .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Taken together , this is the first detailed annotated ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"complete genomic sequence of a new genotype PHEV strain in China .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}]}"}]}
{"paper_id": "4023e727f2e03b241546a3cc98972ce3eb578d95", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nVirus discovery based on cDNA-AFLP ( amplified fragment length polymorphism ) ( VIDISCA ) is a novel approach that provides a fast and effective tool for amplification of unknown genomes , e.g. , of human pathogenic viruses . The VIDISCA method is based on double restriction enzyme processing of a target sequence and ligation of oligonucleotide adaptors that subsequently serve as priming sites for amplification . As the method is based on the common presence of restriction sites , it results in the generation of reproducible , species-specific amplification patterns . The method allows amplification and identification of viral RNA/DNA , with a lower cutoff value of 10 5 copies/ml for DNA viruses and 10 6 copies/ml for the RNA viruses . Previously , we described the identification of a novel human coronavirus , HCoV-NL63 , with the use of the VIDISCA method .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Virus discovery based on cDNA-AFLP ( amplified fragment length polymorphism ) ( VIDISCA ) is a novel approach that provides a fast and effective tool for amplification of unknown genomes ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"e.g. , of human pathogenic viruses .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"The VIDISCA method is based on double restriction enzyme processing of a target sequence and ligation of oligonucleotide adaptors that subsequently serve as priming sites for amplification .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"As the method is based on the common presence of restriction sites ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"it results in the generation of reproducible , species-specific amplification patterns .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"The method allows amplification and identification of viral RNA/DNA ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"with a lower cutoff value of 10 5 copies/ml for DNA viruses and 10 6 copies/ml for the RNA viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Previously , we described the identification of a novel human coronavirus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"HCoV-NL63 , with the use of the VIDISCA method .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}]}"}]}
{"paper_id": "dece55ca4326ff6107a8b0fffc67afdccfeb9d51", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nDengue virus ( DV ) infection depends on a step of membrane fusion , which occurs in the acidic environment of the endosome . This process is mediated by virus surface envelope glycoprotein , in which the loop between residues D98-G112 is considered to be crucial , acting as a fusion peptide . Here , we have characterized functionally and structurally the interaction between the DV fusion peptide and different model membranes by fluorescence and NMR . Its interaction was strongest in dodecylphosphocholine ( DPC ) micelles and anionic phosphatidylcholine/phosphatidylglycerol vesicles , the only vesicle that was fused by DV fusion peptide . The three-dimensional structure of DV fusion peptide bound to DPC micelles was solved by solution homonuclear NMR with an r.m.s.d. of 0.98 Å . The most striking result obtained from the solution structure was the hydrophobic triad formed by residues W101 , L107 , and F108 , pointing toward the same direction , keeping the segment between G102 and G106 in a loop conformation . The interaction of DV fusion peptide with phosphatidylcholine/phosphatidylglycerol vesicles was also mapped by transfer-nuclear Overhauser enhancement ( NOE ) experiments , in which the majority of the NOE cross-peaks were from the hydrophobic triad , corroborating the DPCbound structure . Substitution of the residue W101 by an alanine residue completely abolished membrane binding and , thus , fusion by the peptide and its NOE cross-peaks . In conclusion , the 15-residue DV fusion peptide has intrinsic ability to promote membrane fusion , most likely due to the hydrophobic interaction among the residues W101 , L107 , and F108 , which maintains its loop in the correct spatial conformation .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Dengue virus ( DV ) infection depends on a step of membrane fusion ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"which occurs in the acidic environment of the endosome .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"This process is mediated by virus surface envelope glycoprotein ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"in which the loop between residues D98-G112 is considered to be crucial ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"acting as a fusion peptide .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Here , we have characterized functionally and structurally the interaction between the DV fusion peptide and different model membranes by fluorescence and NMR .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Its interaction was strongest in dodecylphosphocholine ( DPC ) micelles and anionic phosphatidylcholine/phosphatidylglycerol vesicles ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"the only vesicle that was fused by DV fusion peptide .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The three-dimensional structure of DV fusion peptide bound to DPC micelles was solved by solution homonuclear NMR with an r.m.s.d. of 0.98 Å .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"The most striking result obtained from the solution structure was the hydrophobic triad formed by residues W101 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"L107 , and F108 , pointing toward the same direction ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"keeping the segment between G102 and G106 in a loop conformation .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"The interaction of DV fusion peptide with phosphatidylcholine/phosphatidylglycerol vesicles was also mapped by transfer-nuclear Overhauser enhancement ( NOE ) experiments ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"in which the majority of the NOE cross-peaks were from the hydrophobic triad , corroborating the DPCbound structure .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"Substitution of the residue W101 by an alanine residue completely abolished membrane binding and ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"thus , fusion by the peptide and its NOE cross-peaks .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"In conclusion , the 15-residue DV fusion peptide has intrinsic ability to promote membrane fusion ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"most likely due to the hydrophobic interaction among the residues W101 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"L107 , and F108 , which maintains its loop in the correct spatial conformation .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}]}"}]}
{"paper_id": "194e09560f46554663015f54423f7f5d7822025b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nEarly disease diagnostics require rapid , sensitive , and selective detection methods for target analytes . Specifically , early viral detection in a point-of-care setting is critical in preventing epidemics and the spread of disease . However , conventional methods such as enzyme-linked immunosorbent assays or cell cultures are cumbersome and difficult for field use due to the requirements of extensive lab equipment and highly trained personnel , as well as limited sensitivity . Recent advances in nanoparticle concentration have given rise to many novel detection methodologies , which address the shortcomings in modern clinical assays . Here , we review the primary , well-characterized methods for nanoparticle concentration in the context of viral detection via diffusion , centrifugation and microfiltration , electric and magnetic fields , and nano-microfluidics . Details of the concentration mechanisms and examples of related applications provide valuable information to design portable , integrated sensors . This study reviews a wide range of concentration techniques and compares their advantages and disadvantages with respect to viral particle detection . We conclude by highlighting selected concentration methods and devices for next-generation biosensing systems .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Early disease diagnostics require rapid ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"sensitive , and selective detection methods for target analytes .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Specifically , early viral detection in a point-of-care setting is critical in preventing epidemics and the spread of disease .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"However , conventional methods such as enzyme-linked immunosorbent assays or cell cultures are cumbersome and difficult for field use due to the requirements of extensive lab equipment and highly trained personnel ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"as well as limited sensitivity .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Recent advances in nanoparticle concentration have given rise to many novel detection methodologies ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"which address the shortcomings in modern clinical assays .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Here , we review the primary ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"well-characterized methods for nanoparticle concentration in the context of viral detection via diffusion ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}, {\"segment_text\": \"centrifugation and microfiltration , electric and magnetic fields , and nano-microfluidics .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 10}, {\"segment_text\": \"Details of the concentration mechanisms and examples of related applications provide valuable information to design portable , integrated sensors .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 11}, {\"segment_text\": \"This study reviews a wide range of concentration techniques and compares their advantages and disadvantages with respect to viral particle detection .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}, {\"segment_text\": \"We conclude by highlighting selected concentration methods and devices for next-generation biosensing systems .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "5a5a7b6d40c4b752aabf69f69bbd7c71e2658e8e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nChina reported zero locally-acquired malaria cases in 2017 and 2018 . Understanding the spatio-9 temporal pattern underlying this decline , especially the relationship between locally-acquired and 10 imported cases , can inform efforts to maintain elimination and prevent re-emergence . This is 11 particularly pertinent in Yunnan province , where the potential for local transmission is highest . Using 12 a geo-located individual-level dataset of cases recorded in Yunnan province between 2011 and 2016 , 13 we jointly estimate the case reproduction number , , and the number of unobserved sources of 14 infection . We use these estimates within spatio-temporal geostatistical models to map how 15 transmission varied over time and space , estimate the timeline to elimination and the risk of 16 resurgence . Our estimates suggest that , maintaining current intervention efforts , Yunnan is unlikely 17 to experience sustained local transmission up to 2020 . However , even with a mean of 0.005 18 projected for the year 2019 , locally-acquired cases are possible due to high levels of importation .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"China reported zero locally-acquired malaria cases in 2017 and 2018 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Understanding the spatio-9 temporal pattern underlying this decline ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"especially the relationship between locally-acquired and 10 imported cases ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"can inform efforts to maintain elimination and prevent re-emergence .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"This is 11 particularly pertinent in Yunnan province ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"where the potential for local transmission is highest .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Using 12 a geo-located individual-level dataset of cases recorded in Yunnan province between 2011 and 2016 , 13\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"we jointly estimate the case reproduction number ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \", and the number of unobserved sources of 14 infection .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"We use these estimates within spatio-temporal geostatistical models to map how 15 transmission varied over time and space ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"estimate the timeline to elimination and the risk of 16 resurgence .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Our estimates suggest that , maintaining current intervention efforts ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Yunnan is unlikely 17 to experience sustained local transmission up to 2020 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"However , even with a mean of 0.005 18 projected for the year 2019 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"locally-acquired cases are possible due to high levels of importation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}]}"}]}
{"paper_id": "2e9afff6dbd13e0f5a4cd903bc870efeaf4c883b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground-Healthcare-associated transmission of respiratory viruses is a concerning patient safety issue . Design-Surveillance for influenza virus among a cohort of healthcare workers ( HCWs ) was conducted in a tertiary care children 's hospital from November 2009 until April 2010 , using biweekly nasal swab collection . If a subject reported respiratory symptoms , an additional specimen was collected . Specimens from ill HCWs and a randomly selected sample from asymptomatic subjects were tested for additional respiratory viruses by multiplex PCR . Results-From 170 enrolled subjects , 1404 nasal swabs were collected . Influenza circulated at very low levels during the surveillance period and 74.2 % of subjects received influenza vaccination . Influenza was not detected in any specimen . Multiplex respiratory virus PCR analysis of all 119 samples from symptomatic subjects and 200 specimens from asymptomatic subjects yielded a total of 42 positive specimens ; 7 ( 16.7 % ) in asymptomatic subjects . Viral shedding was associated with report of any symptom ( OR 13.06 , p < 0.0001 , ) and younger age ( OR 0.96 , p = 0.023 , 95 % CI 0.92-0.99 ) when controlled for gender and occupation of physician or nurse . After the surveillance period , 46 % of subjects reported working while ill with an influenza-like illness during the previous influenza season .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background-Healthcare-associated transmission of respiratory viruses is a concerning patient safety issue .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Design-Surveillance for influenza virus among a cohort of healthcare workers ( HCWs ) was conducted in a tertiary care children 's hospital from November 2009 until April 2010 ,\", \"label\": \"purpose\", \"decision_reference\": \"boundary background_vs_purpose\", \"id\": 2}, {\"segment_text\": \"using biweekly nasal swab collection .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"If a subject reported respiratory symptoms ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"an additional specimen was collected .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Specimens from ill HCWs and a randomly selected sample from asymptomatic subjects were tested for additional respiratory viruses by multiplex PCR .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Results-From 170 enrolled subjects , 1404 nasal swabs were collected .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"Influenza circulated at very low levels during the surveillance period and 74.2 % of subjects received influenza vaccination .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"Influenza was not detected in any specimen .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Multiplex respiratory virus PCR analysis of all 119 samples from symptomatic subjects and 200 specimens from asymptomatic subjects yielded a total of 42 positive specimens ; 7 ( 16.7 % ) in asymptomatic subjects .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"Viral shedding was associated with report of any symptom ( OR 13.06 , p < 0.0001 , ) and younger age ( OR 0.96 , p = 0.023 , 95 % CI 0.92-0.99 ) when controlled for gender and occupation of physician or nurse .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"After the surveillance period , 46 % of subjects reported working while ill with an influenza-like illness during the previous influenza season .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}]}"}]}
{"paper_id": "d5794d9e687b1087383f2bca0c5beaf31ebc2955", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Epidemiological interventions aim to control the spread of infectious disease through various mechanisms , each carrying a different associated cost . Methodology : We describe a flexible statistical framework for generating optimal epidemiological interventions that are designed to minimize the total expected cost of an emerging epidemic while simultaneously propagating uncertainty regarding the underlying disease model parameters through to the decision process . The strategies produced through this framework are adaptive : vaccination schedules are iteratively adjusted to reflect the anticipated trajectory of the epidemic given the current population state and updated parameter estimates . Conclusions : Using simulation studies based on a classic influenza outbreak , we demonstrate the advantages of adaptive interventions over non-adaptive ones , in terms of cost and resource efficiency , and robustness to model misspecification .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Epidemiological interventions aim to control the spread of infectious disease through various mechanisms ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"each carrying a different associated cost .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Methodology : We describe a flexible statistical framework for generating optimal epidemiological interventions that are designed to minimize the total expected cost of an emerging epidemic while simultaneously propagating uncertainty regarding the underlying disease model parameters through to the decision process .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"The strategies produced through this framework are adaptive : vaccination schedules are iteratively adjusted to reflect the anticipated trajectory of the epidemic given the current population state and updated parameter estimates .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Conclusions : Using simulation studies based on a classic influenza outbreak ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"we demonstrate the advantages of adaptive interventions over non-adaptive ones ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"in terms of cost and resource efficiency ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"and robustness to model misspecification .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}]}"}]}
{"paper_id": "365ab3e4ca40537484abf16d4d33d88f63635404", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMiddle East Respiratory Syndrome ( MERS ) , a pandemic threat to human beings , has aroused huge concern worldwide , but no bibliometric studies have been conducted on MERS research . The aim of this study was to map research productivity on the disease based on the articles indexed in PubMed . The articles related to MERS dated from 2012 to 2015 were retrieved from PubMed . The articles were classified into three categories according to their focus . Publication outputs were assessed and frequently used terms were mapped using the VOS viewer software . A total of 443 articles were included for analysis . They were published in 162 journals , with Journal of Virology being the most productive ( 44 articles ; 9.9 % ) and by six types of organizations , with universities being the most productive ( 276 articles ; 62.4 % ) . The largest proportion of the articles focused on basic medical sciences and clinical studies ( 47.2 % ) and those on prevention and control ranked third ( 26.2 % ) , with those on other focuses coming in between ( 26.6 % ) . The articles on prevention and control had the highest mean rank for impact factor ( IF ) ( 226.34 ) , followed by those on basic medical sciences and clinical studies ( 180.23 ) and those on other focuses ( 168.03 ) . The mean rank differences were statistically significant ( p = 0.000 ) . Besides , `` conronavirus '' , `` case '' , `` transmission '' and `` detection '' were found to be the most frequently used terms . The findings of this first bibliometric study on MERS suggest that the prevention and control of the disease has become a big concern and related research should be strengthened .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Middle East Respiratory Syndrome ( MERS ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"a pandemic threat to human beings ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"has aroused huge concern worldwide ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"but no bibliometric studies have been conducted on MERS research .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"The aim of this study was to map research productivity on the disease based on the articles indexed in PubMed .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"The articles related to MERS dated from 2012 to 2015 were retrieved from PubMed .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"The articles were classified into three categories according to their focus .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Publication outputs were assessed and frequently used terms were mapped using the VOS viewer software .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"A total of 443 articles were included for analysis .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"They were published in 162 journals ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"with Journal of Virology being the most productive ( 44 articles ; 9.9 % ) and by six types of organizations ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"with universities being the most productive ( 276 articles ; 62.4 % ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"The largest proportion of the articles focused on basic medical sciences and clinical studies ( 47.2 % ) and those on prevention and control ranked third ( 26.2 % ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"with those on other focuses coming in between ( 26.6 % ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"The articles on prevention and control had the highest mean rank for impact factor ( IF ) ( 226.34 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"followed by those on basic medical sciences and clinical studies ( 180.23 ) and those on other focuses ( 168.03 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"The mean rank differences were statistically significant ( p = 0.000 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Besides , `` conronavirus '' ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"`` case '' , `` transmission '' and `` detection '' were found to be the most frequently used terms .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"The findings of this first bibliometric study on MERS suggest that the prevention and control of the disease has become a big concern and related research should be strengthened .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}]}"}]}
{"paper_id": "d7855f0e37fe34ab8dd7d405ceb64fab485f0258", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nWe introduce a new approach to investigate the dual nucleotides compositions of 11 Gram-positive and 12 Gram-negative eubacteria recently studied by Sorimachi and Okayasu . The approach firstly obtains a 16-dimension vector set of dual nucleotides by PN-curve from the complete genome of organism . Each vector of the set corresponds to a single gene of genome . Then we reduce the 16-dimension vector set to 2-dimension by principal components analysis ( PCA ) . The reduction avoids possible loss of information averaging all 16-dimension vectors . Then we suggest a 2D graphical representation based on the 2-dimension vector to investigate the classification patters among different organisms . Crown\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"We introduce a new approach to investigate the dual nucleotides compositions of 11 Gram-positive and 12 Gram-negative eubacteria recently studied by Sorimachi and Okayasu .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"The approach firstly obtains a 16-dimension vector set of dual nucleotides by PN-curve from the complete genome of organism .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"Each vector of the set corresponds to a single gene of genome .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Then we reduce the 16-dimension vector set to 2-dimension by principal components analysis ( PCA ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"The reduction avoids possible loss of information averaging all 16-dimension vectors .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Then we suggest a 2D graphical representation based on the 2-dimension vector to investigate the classification patters among different organisms .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Crown\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 7}]}"}]}
{"paper_id": "1f42f8339d7413027d9fd76e9da31f852a9df34a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nTwo tobacco mosaic virus ( TMV ) - derived replicons , created by deletion of most of the 126/18 $ .40 e open reading frame ( ORF ) , replicated and systemically invaded tobacco plants when sorted by wild type TMV . One RNArepecon contained an internal direct repast of 476 nucleotides from the 3 ' end of the 30-kOa ORF . ARhaugh this ORA was replicated , most of the progeny were heterogeneous in size and smaller than the origin transcript . A aeoand WVderived RPM replicon , without any Internally repeated sequences and containing a deletion of the ! y portion of the 30-kDa ORF as well as most of the 1281183-kDa ORF , was created and coinoculated with wild type TMV as helper . This ANA also wasreplicatedeAk : ientyandsystemicallyinvadedtobaccoplama . Anexaminationofthe ofcONA clones obtained after PCR amplification of the progeny population of this RNA repfibon dernonshrolead a that the observed size heterogeneity was due to deletions and insertions adjacent to the artificially created d1FeNtan junction . Them data demonstrate that a TMV Infection is capable of supporting an artificially created RNA rapfical olnier to defective interfering RNAM or satellites . However , these dependent RNAs were replicated without noticeably interfering with wild type TMV symptoms or replication .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Two tobacco mosaic virus ( TMV ) - derived replicons ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"created by deletion of most of the 126/18 $ .40 e open reading frame ( ORF ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"replicated and systemically invaded tobacco plants when sorted by wild type TMV .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"One RNArepecon contained an internal direct repast of 476 nucleotides from the 3 ' end of the 30-kOa ORF .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"ARhaugh this ORA was replicated ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"most of the progeny were heterogeneous in size and smaller than the origin transcript .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"A aeoand WVderived RPM replicon ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"without any Internally repeated sequences and containing a deletion of the !\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"y portion of the 30-kDa ORF as well as most of the 1281183-kDa ORF ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"was created and coinoculated with wild type TMV as helper .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"This ANA also wasreplicatedeAk : ientyandsystemicallyinvadedtobaccoplama .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Anexaminationofthe ofcONA clones obtained after PCR amplification of the progeny population of this RNA repfibon dernonshrolead a that the observed size heterogeneity was due to deletions and insertions adjacent to the artificially created d1FeNtan junction .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Them data demonstrate that a TMV Infection is capable of supporting an artificially created RNA rapfical olnier to defective interfering RNAM or satellites .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"However , these dependent RNAs were replicated without noticeably interfering with wild type TMV symptoms or replication .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "307f1eb7eb7c63dda32e21c1b25c404442cfbe1e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMonocyte development is a tightly regulated and multi-staged process , occurring through several defined progenitor cell intermediates . The key transcription factors , including PU .1 , IRF8 and KLF4 , growth factors , such as M-CSF and IL-34 and cytokines that drive monocyte development from hematopoietic progenitor cells are well defined . However , the molecular controls that direct differentiation into the Ly6C hi inflammatory and Ly6C lo monocyte subsets are yet to be completely elucidated . This review will provide a summary of the transcriptional regulation of monocyte development . We will also discuss how these molecular controls are also critical for microglial development despite their distinct haematopoetic origins . Furthermore , we will examine recent breakthroughs in defining mechanisms that promote differentiation of specific monocyte subpopulations . • Monocyte development is a tightly regulated molecular process • Transcription factors PU .1 , IRF8 and KLF4 are critical for monocyte development • NR4A1 is critical for Ly6Clo monocyte development from Ly6Chi progenitors\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Monocyte development is a tightly regulated and multi-staged process ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"occurring through several defined progenitor cell intermediates .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"The key transcription factors , including PU .1 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"IRF8 and KLF4 , growth factors ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"such as M-CSF and IL-34 and cytokines that drive monocyte development from hematopoietic progenitor cells are well defined .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"However , the molecular controls that direct differentiation into the Ly6C hi inflammatory and Ly6C lo monocyte subsets are yet to be completely elucidated .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"This review will provide a summary of the transcriptional regulation of monocyte development .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"We will also discuss how these molecular controls are also critical for microglial development despite their distinct haematopoetic origins .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"Furthermore , we will examine recent breakthroughs in defining mechanisms that promote differentiation of specific monocyte subpopulations .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}, {\"segment_text\": \"• Monocyte development is a tightly regulated molecular process • Transcription factors PU .1 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"IRF8 and KLF4 are critical for monocyte development • NR4A1 is critical for Ly6Clo monocyte development from Ly6Chi progenitors\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}]}"}]}
{"paper_id": "94b0b4ff4b0f902dfd657ad09a97c75163b1cd43", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nWe have developed an optimized array-based approach for customizable allele-specific gene expression ( ASE ) analysis . The central features of the approach are the ability to select SNPs at will for detection , and the absence of need to PCR amplify the target . A surprisingly long probe length ( 39-49 nt ) was needed for allelic discrimination . Reconstitution experiments demonstrate linearity of ASE over a broad range . Using this approach , we have discovered at least two novel imprinted genes , NLRP2 , which encodes a member of the inflammasome , and OSBPL1A , which encodes a presumed oxysterol-binding protein , were both preferentially expressed from the maternal allele . In contrast , ERAP2 , which encodes an aminopeptidase , did not show preferential parent-of-origin expression , but rather , cis-acting nonimprinted differential allelic control . The approach is scalable to the whole genome and can be used for discovery of functional epigenetic modifications in patient samples .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"We have developed an optimized array-based approach for customizable allele-specific gene expression ( ASE ) analysis .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"The central features of the approach are the ability to select SNPs at will for detection ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"and the absence of need to PCR amplify the target .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"A surprisingly long probe length ( 39-49 nt ) was needed for allelic discrimination .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Reconstitution experiments demonstrate linearity of ASE over a broad range .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Using this approach , we have discovered at least two novel imprinted genes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"NLRP2 , which encodes a member of the inflammasome ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"and OSBPL1A , which encodes a presumed oxysterol-binding protein ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"were both preferentially expressed from the maternal allele .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"In contrast , ERAP2 , which encodes an aminopeptidase ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"did not show preferential parent-of-origin expression ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"but rather , cis-acting nonimprinted differential allelic control .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"The approach is scalable to the whole genome and can be used for discovery of functional epigenetic modifications in patient samples .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "034cab326c750ea98f621e9c65371b8f139fbfb4", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nInfluenza A viruses ( IAV ) continually evolve and have the capacity to cause global pandemics . Because IAV represents an ongoing threat , identifying novel therapies and host innate immune factors that contribute to IAV pathogenesis is of considerable interest . This review summarizes the relevant literature as it relates to global host responses to influenza infection at both the proteome and transcriptome level . The various-omics infection systems that include but are not limited to ferrets , mice , pigs , and even the controlled infection of humans are reviewed . Discussion focuses on recent advances , remaining challenges , and knowledge gaps as it relates to influenza-omics infection outcomes . . As IAV strains evolve and sequence information from the IAV can not currently determine pathogenicity , - omics platforms can be a powerful tool to compare emergent IAV strain data with previously circulating strains for the purpose of threat characterization . In the last ten years , mass spectrometry instrumentation and methodology advancements have led to considerable knowledge of the host proteomic response to viral infection ( for a recent review , see ( 1 ) ) . The increasing popularity of NGS technologies such as RNA-seq , in combination with further advances in microarray profiling technology has also increased our transcriptomic-RNA understanding of virus-host interactions . As - omics capabilities become cheaper and the software to interpret data becomes more user-friendly , the number of laboratories that can perform these data-intensive studies will likely increase . The purpose of this review is to assess both proteomic and transcriptomic findings in the context of IAV infection . In the following sections , recent advances and future prospects are discussed . Figure 1 summarizes notable published - omics experiments , many of which are discussed in the proceeding sections .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Influenza A viruses ( IAV ) continually evolve and have the capacity to cause global pandemics .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Because IAV represents an ongoing threat ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"identifying novel therapies and host innate immune factors that contribute to IAV pathogenesis is of considerable interest .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"This review summarizes the relevant literature as it relates to global host responses to influenza infection at both the proteome and transcriptome level .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"The various-omics infection systems that include but are not limited to ferrets ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"mice , pigs , and even the controlled infection of humans are reviewed .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Discussion focuses on recent advances ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"remaining challenges , and knowledge gaps as it relates to influenza-omics infection outcomes .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \".\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 9}, {\"segment_text\": \"As IAV strains evolve and sequence information from the IAV can not currently determine pathogenicity ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"- omics platforms can be a powerful tool to compare emergent IAV strain data with previously circulating strains for the purpose of threat characterization .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"In the last ten years ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"mass spectrometry instrumentation and methodology advancements have led to considerable knowledge of the host proteomic response to viral infection ( for a recent review , see ( 1 ) ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}, {\"segment_text\": \"The increasing popularity of NGS technologies such as RNA-seq ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 14}, {\"segment_text\": \"in combination with further advances in microarray profiling technology has also increased our transcriptomic-RNA understanding of virus-host interactions .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 15}, {\"segment_text\": \"As - omics capabilities become cheaper and the software to interpret data becomes more user-friendly ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 16}, {\"segment_text\": \"the number of laboratories that can perform these data-intensive studies will likely increase .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 17}, {\"segment_text\": \"The purpose of this review is to assess both proteomic and transcriptomic findings in the context of IAV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"In the following sections , recent advances and future prospects are discussed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Figure 1 summarizes notable published - omics experiments ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"many of which are discussed in the proceeding sections .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}]}"}]}
{"paper_id": "5bd9a33c12874606f5cd2cf9ad4ee1baf09cf8fc", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCategory A arenaviruses as defined by the National Institute of Allergy and Infectious Diseases ( NIAID ) are human pathogens that could be weaponized by bioterrorists . Many of these deadly viruses require biosafety level-4 ( BSL-4 ) containment for all laboratory work , which limits traditional laboratory high-throughput screening ( HTS ) for identification of small molecule inhibitors . For those reasons , a related BSL-2 New World arenavirus , Tacaribe virus , 67-78 % identical to Junín virus at the amino acid level , was used in a HTS campaign where approximately 400,000 small molecule compounds were screened in a Tacaribe virus-induced cytopathic effect ( CPE ) assay . Compounds identified in this screen showed antiviral activity and specificity against not only Tacaribe virus , but also the Category A New World arenaviruses ( Junín , Machupo , and Guanarito ) . Drug resistant variants were isolated , suggesting that these compounds act through inhibition of a viral protein , the viral glycoprotein ( GP2 ) , and not through cellular toxicity mechanisms . A lead compound , ST-294 , has been chosen for drug development . This potent and selective compound , with good bioavailability , demonstrated protective anti-viral efficacy in a Tacaribe mouse challenge model . This series of compounds represent a new class of inhibitors that may warrant further development for potential inclusion in a strategic stockpile .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Category A arenaviruses as defined by the National Institute of Allergy and Infectious Diseases ( NIAID ) are human pathogens that could be weaponized by bioterrorists .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Many of these deadly viruses require biosafety level-4 ( BSL-4 ) containment for all laboratory work ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"which limits traditional laboratory high-throughput screening ( HTS ) for identification of small molecule inhibitors .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"For those reasons , a related BSL-2 New World arenavirus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Tacaribe virus , 67-78 % identical to Junín virus at the amino acid level ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"was used in a HTS campaign where approximately 400,000 small molecule compounds were screened in a Tacaribe virus-induced cytopathic effect ( CPE ) assay .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Compounds identified in this screen showed antiviral activity and specificity against not only Tacaribe virus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"but also the Category A New World arenaviruses ( Junín , Machupo , and Guanarito ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"Drug resistant variants were isolated ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"suggesting that these compounds act through inhibition of a viral protein ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"the viral glycoprotein ( GP2 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and not through cellular toxicity mechanisms .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"A lead compound , ST-294 ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}, {\"segment_text\": \"has been chosen for drug development .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 14}, {\"segment_text\": \"This potent and selective compound ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"with good bioavailability , demonstrated protective anti-viral efficacy in a Tacaribe mouse challenge model .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"This series of compounds represent a new class of inhibitors that may warrant further development for potential inclusion in a strategic stockpile .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "6999b89c08c8a72fc0e86e78e4fd67666516a63a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nNosocomial infections are a major worldwide cause of death and disability , infection control programs are effective in limiting these infections , especially those acquired in the intensive care unit . The development of the world wide web has provided health care professionals with immediate access to continuously updated information in the field of infection control . We sought to identify websites that contain information on nosocomial infection control by using popular internet search engines , such as Google , Yahoo and AltaVista , and by reviewing relevant publications identified in the PubMed and Current Contents databases . Only those sites that were English language , open access , and developed by a government , academic institution , or national or international scientific association were eligible for inclusion . From a vast number of internet sites initially identified , we selected 49 that provide information on infection control for inclusion in our list of practical and relevant internet resources . Several sites provide general information on infection control practices , whereas others focus on one or a few specific infection ( s ) . We provide health care professionals with a timely and succinct list of open access internet resources that contain information regarding the prevention and control of nosocomial infections in order to help in the dissemination of relevant information and so contribute to the limitation of such hazards . Good collection of preventive measures for infection control http://www.health.gov.au/internet/wcms/Publishing.nsf/content/ Infection control guidelines for the prevention of transmission of infectious icg-guidelines-index.htm diseases in the health care setting http://www.nice.org.uk/page.aspx?o=CG002 Provides a set of measures to avoid infection that should be followed by anyone giving or receiving care at home or at a health centre http://www.cdc.gov/ncidod/dhqp/index.html Guidelines for keeping patients and health care workers in health care settings protected from infectious diseases http://www.nhsplus.nhs.uk/nhsstaff/infection.asp Limited information\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Nosocomial infections are a major worldwide cause of death and disability ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"infection control programs are effective in limiting these infections ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"especially those acquired in the intensive care unit .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"The development of the world wide web has provided health care professionals with immediate access to continuously updated information in the field of infection control .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"We sought to identify websites that contain information on nosocomial infection control by using popular internet search engines ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"such as Google , Yahoo and AltaVista ,\", \"label\": \"purpose\", \"decision_reference\": \"boundary background_vs_purpose\", \"id\": 6}, {\"segment_text\": \"and by reviewing relevant publications identified in the PubMed and Current Contents databases .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Only those sites that were English language ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"open access , and developed by a government ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"academic institution , or national or international scientific association were eligible for inclusion .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"From a vast number of internet sites initially identified ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"we selected 49 that provide information on infection control for inclusion in our list of practical and relevant internet resources .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"Several sites provide general information on infection control practices ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"whereas others focus on one or a few specific infection ( s ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"We provide health care professionals with a timely and succinct list of open access internet resources that contain information regarding the prevention and control of nosocomial infections in order to help in the dissemination of relevant information and so contribute to the limitation of such hazards .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Good collection of preventive measures for infection control http://www.health.gov.au/internet/wcms/Publishing.nsf/content/ Infection control guidelines for the prevention of transmission of infectious icg-guidelines-index.htm diseases in the health care setting http://www.nice.org.uk/page.aspx?o=CG002\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Provides a set of measures to avoid infection that should be followed by anyone giving or receiving care at home or at a health centre http://www.cdc.gov/ncidod/dhqp/index.html Guidelines for keeping patients and health care workers in health care settings protected from infectious diseases http://www.nhsplus.nhs.uk/nhsstaff/infection.asp Limited information\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "8190ea84cdfa846568cdac1f77111d9505ec399b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe basic reproduction number R 0 is one of the most important concepts in modern infectious disease epidemiology . However , for more realistic and more complex models than those assuming homogeneous mixing in the population , other threshold quantities can be defined that are sometimes more useful and easily derived in terms of model parameters . In this paper , we present a model for the spread of a permanently immunizing infection in a population socially structured into households and workplaces/schools , and we propose and discuss a new household-to-household reproduction number R H for it . We show how R H overcomes some of the limitations of a previously proposed threshold parameter , and we highlight its relationship with the effort required to control an epidemic when interventions are targeted at randomly selected households .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The basic reproduction number R 0 is one of the most important concepts in modern infectious disease epidemiology .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"However , for more realistic and more complex models than those assuming homogeneous mixing in the population ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"other threshold quantities can be defined that are sometimes more useful and easily derived in terms of model parameters .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"In this paper , we present a model for the spread of a permanently immunizing infection in a population socially structured into households and workplaces/schools ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"and we propose and discuss a new household-to-household reproduction number R H for it .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"We show how R H overcomes some of the limitations of a previously proposed threshold parameter ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"and we highlight its relationship with the effort required to control an epidemic when interventions are targeted at randomly selected households .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}]}"}]}
{"paper_id": "ab0c7dec09cd27954e7f45caacfd45fef11404bf", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nHydroxychloroquine ( HCQ ) is an antimalarial drug also used in treating autoimmune diseases . Its antiviral activity was demonstrated in restricting HIV infection in vitro ; however , the clinical implications remain controversial . Infection with dengue virus ( DENV ) is a global public health problem , and we lack an antiviral drug for DENV . Here , we evaluated the anti-DENV potential of treatment with HCQ . Immunofluorescence assays demonstrated that HCQ could inhibit DENV serotype 1-4 infection in vitro . RT-qPCR analysis of HCQtreated cells showed induced expression of interferon ( IFN ) - related antiviral proteins and certain inflammatory cytokines . Mechanistic study suggested that HCQ activated the innate immune signaling pathways of IFN-b , AP-1 , and NFkB . Knocking down mitochondrial antiviral signaling protein ( MAVS ) , inhibiting TANK binding kinase 1 ( TBK1 ) / inhibitor-kB kinase e ( IKKe ) , and blocking type I IFN receptor reduced the efficiency of HCQ against DENV-2 infection . Furthermore , HCQ significantly induced cellular production of reactive oxygen species ( ROS ) , which was involved in the host defense system . Suppression of ROS production attenuated the innate immune activation and anti-DENV-2 effect of HCQ . In summary , HCQ triggers the host defense machinery by inducing ROS-and MAVS-mediated innate immune activation against DENV infection and may be a candidate drug for DENV infection .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Hydroxychloroquine ( HCQ ) is an antimalarial drug also used in treating autoimmune diseases .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Its antiviral activity was demonstrated in restricting HIV infection in vitro ; however ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"the clinical implications remain controversial .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Infection with dengue virus ( DENV ) is a global public health problem ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"and we lack an antiviral drug for DENV .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Here , we evaluated the anti-DENV potential of treatment with HCQ .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"Immunofluorescence assays demonstrated that HCQ could inhibit DENV serotype 1-4 infection in vitro .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"RT-qPCR analysis of HCQtreated cells showed induced expression of interferon ( IFN ) - related antiviral proteins and certain inflammatory cytokines .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Mechanistic study suggested that HCQ activated the innate immune signaling pathways of IFN-b , AP-1 , and NFkB .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Knocking down mitochondrial antiviral signaling protein ( MAVS ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"inhibiting TANK binding kinase 1 ( TBK1 ) / inhibitor-kB kinase e ( IKKe ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and blocking type I IFN receptor reduced the efficiency of HCQ against DENV-2 infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Furthermore , HCQ significantly induced cellular production of reactive oxygen species ( ROS ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"which was involved in the host defense system .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Suppression of ROS production attenuated the innate immune activation and anti-DENV-2 effect of HCQ .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"In summary , HCQ triggers the host defense machinery by inducing ROS-and MAVS-mediated innate immune activation against DENV infection and may be a candidate drug for DENV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "d6631a0f06bb98c73bfde3c98faf886c8be05522", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Effectively responding to infectious disease outbreaks requires a well-informed response . Quantitative methods for analyzing outbreak data and estimating key parameters to characterize the spread of the outbreak , including the reproductive number and the serial interval , often assume that the data collected is complete . In reality reporting delays , undetected cases or lack of sensitive and specific tests to diagnose disease lead to reporting errors in the case counts . Here we provide insight on the impact that such reporting errors might have on the estimation of these key parameters . Results : We show that when the proportion of cases reported is changing through the study period , the estimates of key epidemiological parameters are biased . Using data from the Influenza A/H1N1 outbreak in La Gloria , Mexico , we provide estimates of these parameters , accounting for possible reporting errors , and show that they can be biased by as much as 33 % , if reporting issues are not accounted for . Conclusions : Failure to account for missing data can lead to misleading and inaccurate estimates of epidemic parameters .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Effectively responding to infectious disease outbreaks requires a well-informed response .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Quantitative methods for analyzing outbreak data and estimating key parameters to characterize the spread of the outbreak ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"including the reproductive number and the serial interval ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"often assume that the data collected is complete .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"In reality reporting delays , undetected cases or lack of sensitive and specific tests to diagnose disease lead to reporting errors in the case counts .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Here we provide insight on the impact that such reporting errors might have on the estimation of these key parameters .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"Results : We show that when the proportion of cases reported is changing through the study period ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"the estimates of key epidemiological parameters are biased .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Using data from the Influenza A/H1N1 outbreak in La Gloria ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Mexico , we provide estimates of these parameters ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"accounting for possible reporting errors ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and show that they can be biased by as much as 33 % ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"if reporting issues are not accounted for .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Conclusions : Failure to account for missing data can lead to misleading and inaccurate estimates of epidemic parameters .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "6abf26a75303e6fd937d197e246d6d72e9552c4e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nObjective-To evaluate clinical manifestations , response to treatment , and outcome for Weimaraners with hypertrophic osteodystrophy ( HOD ) . Design-Retrospective case series . Procedures-Medical records were reviewed for signalment , vaccination history , clinical signs , laboratory test results , response to treatment , and relapses . Radiographs were reviewed . Results-Clinical signs included pyrexia , lethargy , and ostealgia ; signs involving the gastrointestinal , ocular , or cutaneous systems were detected . Of the 53 dogs , 28 ( 52.8 % ) had HOD-affected littermates . Dogs with HOD-affected littermates were more likely to relapse , compared with the likelihood of relapse for dogs with no HOD-affected littermates . All 53 dogs had been vaccinated 1 to 30 days before HOD onset ; no difference was found between the number of dogs with a history of vaccination with a recombinant vaccine ( n = 21 ) versus a nonrecombinant vaccine ( 32 ) . Fifty ( 94.3 % ) dogs had radiographic lesions compatible with HOD at disease onset , and the other 3 ( 5.7 % ) had HOD lesions 48 to 72 hours after the onset of clinical signs . Twelve of 22 ( 54.5 % ) dogs treated with NSAIDs did not achieve remission by 7 days after initiation of treatment . All dogs treated initially with corticosteroids achieved remission within 8 to 48 hours . Of the 33 dogs that reached adulthood , 28 ( 84.8 % ) were healthy and 5 ( 15.2 % ) had episodes of pyrexia and malaise . Conclusions and Clinical Relevance-Treatment with corticosteroids was superior to treatment with NSAIDs in Weimaraners with HOD . It may be necessary to evaluate repeated radiographs to establish a diagnosis of HOD . Most HOD-affected Weimaraners had resolution of the condition with physeal closure .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Objective-To evaluate clinical manifestations , response to treatment ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"and outcome for Weimaraners with hypertrophic osteodystrophy ( HOD ) .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"Design-Retrospective case series .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Procedures-Medical records were reviewed for signalment ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"vaccination history , clinical signs ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"laboratory test results , response to treatment , and relapses .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Radiographs were reviewed .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Results-Clinical signs included pyrexia , lethargy ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and ostealgia ; signs involving the gastrointestinal ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"ocular , or cutaneous systems were detected .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Of the 53 dogs , 28 ( 52.8 % ) had HOD-affected littermates .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Dogs with HOD-affected littermates were more likely to relapse ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"compared with the likelihood of relapse for dogs with no HOD-affected littermates .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"All 53 dogs had been vaccinated 1 to 30 days before HOD onset ; no difference was found between the number of dogs with a history of vaccination with a recombinant vaccine ( n = 21 ) versus a nonrecombinant vaccine ( 32 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Fifty ( 94.3 % ) dogs had radiographic lesions compatible with HOD at disease onset ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"and the other 3 ( 5.7 % ) had HOD lesions 48 to 72 hours after the onset of clinical signs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Twelve of 22 ( 54.5 % ) dogs treated with NSAIDs did not achieve remission by 7 days after initiation of treatment .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"All dogs treated initially with corticosteroids achieved remission within 8 to 48 hours .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Of the 33 dogs that reached adulthood ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"28 ( 84.8 % ) were healthy and 5 ( 15.2 % ) had episodes of pyrexia and malaise .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"Conclusions and Clinical Relevance-Treatment with corticosteroids was superior to treatment with NSAIDs in Weimaraners with HOD .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"It may be necessary to evaluate repeated radiographs to establish a diagnosis of HOD .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"Most HOD-affected Weimaraners had resolution of the condition with physeal closure .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}]}"}]}
{"paper_id": "8605d9a84e827e232a47861c65c61605c789acf7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Pandemic influenza A ( H1N1 ) virus emerged in North America in April 2009 and spread globally . We describe the epidemiology and public health response to the first known outbreak of 2009 H1N1 in a train , which occurred in June 2009 in China . Methods : After 2 provinces provided initial reports of 2009 H1N1 infection in 2 persons who had travelled on the same train , we conducted a retrospective epidemiologic investigation to collect information from the passengers , crew members , contacts , and health care providers . We explored the source of infection and possible routes of transmission in the train . All cases were confirmed by real-time reverse transcription polymerase chain reaction testing . Results : Train # 1223 traveled 40 hours , made 28 stops in 4 Chinese provinces , and boarded 2555 passengers , who logged a total of 59 144 person-hours of travel time . Nineteen confirmed 2009 H1N1 cases were identified . Of these , 13 were infected and developed symptoms on the train and 6 occurred among contacts who developed illness during medical monitoring . In addition , 3 asymptomatic cases were identified based on RT-PCR testing of respiratory swabs from contacts . The attack rate among contacts of confirmed cases in the same car was higher than that among contacts in other cars ( 3.15 % vs. 0 % , P < 0.001 ) . Attack rates increased with exposure time . Conclusions : Close contact and long exposure may have contributed to the transmission of 2009 H1N1 virus in the train . Trains may have played an important role in the 2009 influenza pandemic .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Pandemic influenza A ( H1N1 ) virus emerged in North America in April 2009 and spread globally .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"We describe the epidemiology and public health response to the first known outbreak of 2009 H1N1 in a train ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"which occurred in June 2009 in China .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"Methods : After 2 provinces provided initial reports of 2009 H1N1 infection in 2 persons who had travelled on the same train ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"we conducted a retrospective epidemiologic investigation to collect information from the passengers ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"crew members , contacts , and health care providers .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"We explored the source of infection and possible routes of transmission in the train .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"All cases were confirmed by real-time reverse transcription polymerase chain reaction testing .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Results : Train # 1223 traveled 40 hours ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"made 28 stops in 4 Chinese provinces ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"and boarded 2555 passengers , who logged a total of 59 144 person-hours of travel time .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"Nineteen confirmed 2009 H1N1 cases were identified .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"Of these , 13 were infected and developed symptoms on the train and 6 occurred among contacts who developed illness during medical monitoring .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"In addition , 3 asymptomatic cases were identified based on RT-PCR testing of respiratory swabs from contacts .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"The attack rate among contacts of confirmed cases in the same car was higher than that among contacts in other cars ( 3.15 % vs. 0 % , P < 0.001 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"Attack rates increased with exposure time .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"Conclusions : Close contact and long exposure may have contributed to the transmission of 2009 H1N1 virus in the train .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Trains may have played an important role in the 2009 influenza pandemic .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "3de45e7fef20e727dc730f4cf870f8567c8ec9fc", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe + 1 frameshift mutation , M5631 , which is located in the gene ( oxil ) for cytochrome c oxidase II ( COXII ) of the yeast mitochondrial genome , is suppressed spontaneously to a remarkably high extent ( 20 % -30 % ) . The full-length wild-type COXII produced as a result of suppression allows the mutant strain to grow with a `` leaky '' phenotype on non-fermentable medium . In order to elucidate the factors and interactions involved in this translational suppression , the strain with the frameshift mutation was mutated by MnC12 treatment and a large number of mutants showing restriction of the suppression were isolated . Of 20 mutants exhibiting a strong , restricted , respiration-deficient ( RD ) phenotype , 6 were identified as having mutations in the mitochondrial genome . Furthermore , genetic analyses mapped one mutation to the vicinity of the gene for tRNA pr ° and two others to a region of the tRNA cluster where two-thirds of all mitochondrial tRNA genes are encoded . The degree of restriction of the spontaneous frameshift suppression was characterized at the translational level by in vivo 3SS-labeling of the mitochondrial translational products and immunoblotting . These results showed that in some of these mutant strains the frameshift suppression product is synthesized to the same extent as in the leaky parent strain . It is suggested that more than one ÷ 1 frame-shifted product is made as a result of suppression in these strains : one is as functional as the wild-type COXII , the other ( s ) is ( are ) nonfunctional and prevent leaky growth on non-fermentable medium . A possible mechanism for this heterogenous frameshift suppression is discussed .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The + 1 frameshift mutation ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"M5631 , which is located in the gene ( oxil ) for cytochrome c oxidase II ( COXII ) of the yeast mitochondrial genome ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"is suppressed spontaneously to a remarkably high extent ( 20 % -30 % ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The full-length wild-type COXII produced as a result of suppression allows the mutant strain to grow with a `` leaky '' phenotype on non-fermentable medium .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"In order to elucidate the factors and interactions involved in this translational suppression ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"the strain with the frameshift mutation was mutated by MnC12 treatment and a large number of mutants showing restriction of the suppression were isolated .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Of 20 mutants exhibiting a strong ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"restricted , respiration-deficient ( RD ) phenotype ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"6 were identified as having mutations in the mitochondrial genome .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Furthermore , genetic analyses mapped one mutation to the vicinity of the gene for tRNA pr ° and two others to a region of the tRNA cluster where two-thirds of all mitochondrial tRNA genes are encoded .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The degree of restriction of the spontaneous frameshift suppression was characterized at the translational level by in vivo 3SS-labeling of the mitochondrial translational products and immunoblotting .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"These results showed that in some of these mutant strains the frameshift suppression product is synthesized to the same extent as in the leaky parent strain .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"It is suggested that more than one ÷ 1 frame-shifted product is made as a result of suppression in these strains : one is as functional as the wild-type COXII ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"the other ( s ) is ( are ) nonfunctional and prevent leaky growth on non-fermentable medium .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"A possible mechanism for this heterogenous frameshift suppression is discussed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}]}"}]}
{"paper_id": "1196301d4e04f2283f18f95fbbbd6bc5cf6e341f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRift Valley fever virus ( RVFV ) is a highly pathogenic arthropod-borne virus that has a detrimental effect on both livestock and human populations . While there are several diagnostic methodologies available for RVFV detection , many are not sensitive enough to diagnose early infections . Furthermore , detection may be hindered by high abundant proteins such as albumin . Previous findings have shown that Nanotrap particles can be used to significantly enhance detection of various small analytes of low abundance . We have expanded upon this repertoire to show that this simple and efficient sample preparation technology can drastically improve the detection of the RVFV nucleoprotein ( NP ) , the most abundant and widely used viral protein for RVFV diagnostics . This study demonstrates that Nanotrap particles are capable of drastically lowering the limit of detection for RVFV NP by capturing , concentrating , and preserving RVFV NP in clinically relevant matrices . These studies can be extended to a wide range of pathogens and their analytes of diagnostic interest . Nanotrap Particles Enhance the Detection of RVFV Nucleoprotein PLOS ONE |\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Rift Valley fever virus ( RVFV ) is a highly pathogenic arthropod-borne virus that has a detrimental effect on both livestock and human populations .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"While there are several diagnostic methodologies available for RVFV detection ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"many are not sensitive enough to diagnose early infections .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Furthermore , detection may be hindered by high abundant proteins such as albumin .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Previous findings have shown that Nanotrap particles can be used to significantly enhance detection of various small analytes of low abundance .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"We have expanded upon this repertoire to show that this simple and efficient sample preparation technology can drastically improve the detection of the RVFV nucleoprotein ( NP ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"the most abundant and widely used viral protein for RVFV diagnostics .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"This study demonstrates that Nanotrap particles are capable of drastically lowering the limit of detection for RVFV NP by capturing ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"concentrating , and preserving RVFV NP in clinically relevant matrices .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"These studies can be extended to a wide range of pathogens and their analytes of diagnostic interest .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"Nanotrap Particles Enhance the Detection of RVFV Nucleoprotein PLOS ONE |\", \"label\": \"finding\", \"decision_reference\": \"other.definition\", \"id\": 11}]}"}]}
{"paper_id": "e59aeed7153eefa0de4a755d063c59df41044d36", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe abdominal region is the large part of the body extending from the diaphragm to the pelvis . It includes the abdominal and pelvic cavities , bound by bone and muscle . The peritoneum is the largest and most complexly arranged serous membrane in the body . It forms the lining of the peritoneal cavity , which extends in abdominal cavity and contains the gastrointestinal tract ; major abdominal organs , such as the liver , spleen , pancreas , urinary bladder , ovaries , and uterus ; and many nerves , vessels , and lymph nodes . The peritoneum extends caudally in the pelvic cavity in males and females ( as vaginal tunic and vaginal process , respectively ) . It is a serous membrane , divided into the parietal peritoneum , which covers the inner surface of the abdominal wall ( the abdominal fascia ) and the pelvic and scrotal cavities ; the visceral peritoneum , which covers the abdominal , pelvic , and scrotal organs ; and the connecting peritoneum , which extends between organs or between an organ and the parietal peritoneum , forming peritoneal folders that are divided into mesenteries , omenta , and ligaments . The purpose of the peritoneum is to provide a frictionless surface over which the viscera can move . It also serves as a site of fluid transport . A capillary film of serous fluid separates the parietal and visceral layers of the peritoneum from one another and lubricates the peritoneal surfaces . The retroperitoneal region extends dorsal to the peritoneal and pelvic cavities from the diaphragm to the pelvic inlet . It is bordered dorsally by the vertebrae and paraspinal muscles and laterally by the muscular abdominal and pelvic walls . The kidneys , ureters , and adrenal glands are considered to be retroperitoneal organs . The descending aorta , caudal vena cava , lumbar lymph nodes , cisterna chili , lymphatics , fat , and much of the abdominal wall musculature are also are also located in the\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The abdominal region is the large part of the body extending from the diaphragm to the pelvis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"It includes the abdominal and pelvic cavities ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"bound by bone and muscle .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"The peritoneum is the largest and most complexly arranged serous membrane in the body .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"It forms the lining of the peritoneal cavity ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"which extends in abdominal cavity and contains the gastrointestinal tract ; major abdominal organs ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"such as the liver , spleen ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"pancreas , urinary bladder , ovaries ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"and uterus ; and many nerves ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"vessels , and lymph nodes .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"The peritoneum extends caudally in the pelvic cavity in males and females ( as vaginal tunic and vaginal process , respectively ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"It is a serous membrane ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"divided into the parietal peritoneum ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}, {\"segment_text\": \"which covers the inner surface of the abdominal wall ( the abdominal fascia ) and the pelvic and scrotal cavities ; the visceral peritoneum ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 14}, {\"segment_text\": \"which covers the abdominal , pelvic ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 15}, {\"segment_text\": \"and scrotal organs ; and the connecting peritoneum ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 16}, {\"segment_text\": \"which extends between organs or between an organ and the parietal peritoneum ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 17}, {\"segment_text\": \"forming peritoneal folders that are divided into mesenteries , omenta , and ligaments .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 18}, {\"segment_text\": \"The purpose of the peritoneum is to provide a frictionless surface over which the viscera can move .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 19}, {\"segment_text\": \"It also serves as a site of fluid transport .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 20}, {\"segment_text\": \"A capillary film of serous fluid separates the parietal and visceral layers of the peritoneum from one another and lubricates the peritoneal surfaces .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 21}, {\"segment_text\": \"The retroperitoneal region extends dorsal to the peritoneal and pelvic cavities from the diaphragm to the pelvic inlet .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 22}, {\"segment_text\": \"It is bordered dorsally by the vertebrae and paraspinal muscles and laterally by the muscular abdominal and pelvic walls .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 23}, {\"segment_text\": \"The kidneys , ureters , and adrenal glands are considered to be retroperitoneal organs .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 24}, {\"segment_text\": \"The descending aorta , caudal vena cava ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 25}, {\"segment_text\": \"lumbar lymph nodes , cisterna chili ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 26}, {\"segment_text\": \"lymphatics , fat , and much of the abdominal wall musculature are also are also located in the\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 27}]}"}]}
{"paper_id": "9e79c42bd7bcbc8b2fd2ba494815e3df517774a5", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMaria was distraught after reading about the ` potential ' epidemic , yet to happen , and the horror stories on Facebook needing reassurance and certainty about what she should do . She requested an urgent appointment to review her treatment plan . Maria was a 26-year-old woman with relapsing multiple sclerosis who had recently experienced brainstem relapse with double vision and ataxia despite treatment with pegylated interferon-beta for the last 18 months . A brain MRI performed one month prior had shown 16 new T2 lesions , four of which were enhancing . One of the enhancing lesions was at the pontomedullary junction and was certainly the cause of her relapse . Treatment was to be escalated to ocrelizumab with the first dose in a week 's time . In view of the emerging coronavirus pandemic , she was questioning whether or not she should go ahead with ocrelizumab . This was despite only a handful of confirmed COVID-19 cases in the country and none in her town and region . If this scenario sounds plausible what should neurologists do ? Human coronaviruses are predominantly associated with respiratory tract infections and includes those that cause severe acute respiratory syndrome ( SARS ) , Middle East respiratory syndrome ( MERS ) and now the COVID-19 pandemic . In an uncertain world , where we do not have a clear evidence-base , you often have to default to scientific principles , rather than using the wisdom of the crowd . Not surprising , with Italy being one of the epicentres of the COVID-19 epidemic , the Italian society of neurology or SIN ( Società Italiana di Neurologia ) broke cover first producing recommendations on the management of patients with MS during the COVID-19 epidemic ( see Box 1 ) . The SIN guidelines provide relatively straightforward , and one could argue arbitrary , advice on how to manage patients with MS in the short-term , but do not address supervision of these patients in the intermediate or long-term especially those with highly active MS. If the public health measures being taken flatten the peak of the epidemic , but extend its tail , the problem of community-acquired SARS-CoV2 infection and COVID-19 may be with us for many months and potentially years . Are the SIN guidelines compatible with the best interests of our patients or a knee-jerk response to an undefined problem that may not be a problem at all ?\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Maria was distraught after reading about the ` potential ' epidemic ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"yet to happen , and the horror stories on Facebook needing reassurance and certainty about what she should do .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"She requested an urgent appointment to review her treatment plan .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Maria was a 26-year-old woman with relapsing multiple sclerosis who had recently experienced brainstem relapse with double vision and ataxia despite treatment with pegylated interferon-beta for the last 18 months .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"A brain MRI performed one month prior had shown 16 new T2 lesions ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"four of which were enhancing .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"One of the enhancing lesions was at the pontomedullary junction and was certainly the cause of her relapse .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Treatment was to be escalated to ocrelizumab with the first dose in a week 's time .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"In view of the emerging coronavirus pandemic ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"she was questioning whether or not she should go ahead with ocrelizumab .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"This was despite only a handful of confirmed COVID-19 cases in the country and none in her town and region .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"If this scenario sounds plausible what should neurologists do ?\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"Human coronaviruses are predominantly associated with respiratory tract infections and includes those that cause severe acute respiratory syndrome ( SARS ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}, {\"segment_text\": \"Middle East respiratory syndrome ( MERS ) and now the COVID-19 pandemic .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 14}, {\"segment_text\": \"In an uncertain world , where we do not have a clear evidence-base ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 15}, {\"segment_text\": \"you often have to default to scientific principles ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 16}, {\"segment_text\": \"rather than using the wisdom of the crowd .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 17}, {\"segment_text\": \"Not surprising , with Italy being one of the epicentres of the COVID-19 epidemic ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 18}, {\"segment_text\": \"the Italian society of neurology or SIN ( Società Italiana di Neurologia ) broke cover first producing recommendations on the management of patients with MS during the COVID-19 epidemic ( see Box 1 ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 19}, {\"segment_text\": \"The SIN guidelines provide relatively straightforward ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 20}, {\"segment_text\": \"and one could argue arbitrary ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 21}, {\"segment_text\": \"advice on how to manage patients with MS in the short-term ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 22}, {\"segment_text\": \"but do not address supervision of these patients in the intermediate or long-term especially those with highly active MS. If the public health measures being taken flatten the peak of the epidemic ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 23}, {\"segment_text\": \"but extend its tail , the problem of community-acquired SARS-CoV2 infection and COVID-19 may be with us for many months and potentially years .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 24}, {\"segment_text\": \"Are the SIN guidelines compatible with the best interests of our patients or a knee-jerk response to an undefined problem that may not be a problem at all ?\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 25}]}"}]}
{"paper_id": "2b244041ab6f2ab167b76c5b17332c5598b56431", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe current standard care therapy for hepatitis C virus ( HCV ) infection consists of two regimes , namely interferon-based and interferon-free treatments . The treatment through the combination of ribavirin and pegylated interferon is expensive , only mildly effective , and is associated with severe side effects . In 2011 , two direct-acting antiviral ( DAA ) drugs , boceprevir and telaprevir , were licensed that have shown enhanced sustained virologic response ( SVR ) in phase III clinical trial , however , these interferon-free treatments are more sensitive to HCV genotype 1 infection . The variable nature of HCV , and the limited number of inhibitors developed thus aim in expanding the repertoire of available drug targets , resulting in targeting the virus assembly therapeutically . ( isolatek3a ) and HCV genotype 4a ( GT4 ) ( isolateED43 ) . Furthermore , we conducted a quantitative structure-activity relationship and docking interaction study . The drug NB-DNJ formed the highest number of hydrogen bond interactions with both modeled p7 proteins with high interaction energy , followed by BIT225 . A flavonoid screen demonstrated that Epigallocatechin gallate ( EGCG ) , nobiletin , and quercetin , have more binding modes in GT3 than in GT4 . Thus , the predicted p7 protein molecule of HCV from GT3 and GT4 provides a general avenue to target structure-based antiviral compounds . We hypothesize that the inhibitors of viral p7 identified in this screen may be a new class of potent agents , but further confirmation in vitro and in vivo is essential . This structure-guided drug design for both GT3 and GT4 can lead to the identification of drug-like natural compounds , confirming p7 as a new target in the rapidly increasing era of HCV . Computational Docking Study of HCVp7 Ion Channel from Genotype 3 and 4 PLOS ONE |\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The current standard care therapy for hepatitis C virus ( HCV ) infection consists of two regimes ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"namely interferon-based and interferon-free treatments .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The treatment through the combination of ribavirin and pegylated interferon is expensive ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"only mildly effective , and is associated with severe side effects .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"In 2011 , two direct-acting antiviral ( DAA ) drugs ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"boceprevir and telaprevir , were licensed that have shown enhanced sustained virologic response ( SVR ) in phase III clinical trial ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"however , these interferon-free treatments are more sensitive to HCV genotype 1 infection .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"The variable nature of HCV ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"and the limited number of inhibitors developed thus aim in expanding the repertoire of available drug targets ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"resulting in targeting the virus assembly therapeutically .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"( isolatek3a ) and HCV genotype 4a ( GT4 ) ( isolateED43 ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"Furthermore , we conducted a quantitative structure-activity relationship and docking interaction study .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"The drug NB-DNJ formed the highest number of hydrogen bond interactions with both modeled p7 proteins with high interaction energy , followed by BIT225 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"A flavonoid screen demonstrated that Epigallocatechin gallate ( EGCG ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"nobiletin , and quercetin , have more binding modes in GT3 than in GT4 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Thus , the predicted p7 protein molecule of HCV from GT3 and GT4 provides a general avenue to target structure-based antiviral compounds .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"We hypothesize that the inhibitors of viral p7 identified in this screen may be a new class of potent agents ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"but further confirmation in vitro and in vivo is essential .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"This structure-guided drug design for both GT3 and GT4 can lead to the identification of drug-like natural compounds ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"confirming p7 as a new target in the rapidly increasing era of HCV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"Computational Docking Study of HCVp7 Ion Channel from Genotype 3 and 4 PLOS ONE |\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}]}"}]}
{"paper_id": "3a6544f6f247366d4c12167f7fba743e9d981c63", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAngiotensin-converting enzyme 2 ( ACE2 ) has been suggested to be the cellular receptor for the new coronavirus ( 2019-nCoV ) that is causing the coronavirus disease 2019 . Like other coronaviruses such as the SARS-CoV , the 2019-nCoV uses the receptor binding domain ( RBD ) of the surface spike glycoprotein ( S protein ) to engage ACE2 . We most recently determined the structure of the full-length human ACE2 in complex with a neutral amino acid transporter B 0 AT1 . Here we report the cryo-EM structure of the full-length human ACE2 bound to the RBD of the 2019-nCoV at an overall resolution of 2.9 Å in the presence of B 0 AT1 . The local resolution at the ACE2-RBD interface is 3.5 Å , allowing analysis of the detailed interactions between the RBD and the receptor . Similar to that for the SARS-CoV , the RBD of the 2019-nCoV is recognized by the extracellular peptidase domain ( PD ) of ACE2 mainly through polar residues . Pairwise comparison reveals a number of variations that may determine the different affinities between ACE2 and the RBDs from these two related viruses . author/funder . All rights reserved . No reuse allowed without permission .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Angiotensin-converting enzyme 2 ( ACE2 ) has been suggested to be the cellular receptor for the new coronavirus ( 2019-nCoV ) that is causing the coronavirus disease 2019 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Like other coronaviruses such as the SARS-CoV ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"the 2019-nCoV uses the receptor binding domain ( RBD ) of the surface spike glycoprotein ( S protein ) to engage ACE2 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"We most recently determined the structure of the full-length human ACE2 in complex with a neutral amino acid transporter B 0 AT1 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Here we report the cryo-EM structure of the full-length human ACE2 bound to the RBD of the 2019-nCoV at an overall resolution of 2.9 Å in the presence of B 0 AT1 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"The local resolution at the ACE2-RBD interface is 3.5 Å ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"allowing analysis of the detailed interactions between the RBD and the receptor .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Similar to that for the SARS-CoV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"the RBD of the 2019-nCoV is recognized by the extracellular peptidase domain ( PD ) of ACE2 mainly through polar residues .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Pairwise comparison reveals a number of variations that may determine the different affinities between ACE2 and the RBDs from these two related viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"author/funder .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 11}, {\"segment_text\": \"All rights reserved .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 12}, {\"segment_text\": \"No reuse allowed without permission .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 13}]}"}]}
{"paper_id": "2d874577cfbe77f483ae4988cda1975f8d470c91", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMicroglia , unique myeloid cells residing in the brain parenchyma , represent the first line of immune defense within the central nervous system . In addition to their immune functions , microglial cells play an important role in other cerebral processes , including the regulation of synaptic architecture and neurogenesis . Chronic microglial activation is regarded as detrimental , and it is considered a pathogenic mechanism common to several neurological disorders . Microglial activation and function have been extensively studied in rodent experimental models , whereas the characterization of human cells has been limited due to the restricted availability of primary sources of human microglia . To overcome this problem , human immortalized microglial cell lines have been developed . The human microglial clone 3 cell line , HMC3 , was established in 1995 , through SV40-dependent immortalization of human embryonic microglial cells . It has been recently authenticated by the American Type Culture Collection ( ATCC ® ) and distributed under the name of HMC3 ( ATCC ® CRL-3304 ) . The HMC3 cells have been used in six research studies , two of which also indicated by ATCC ® as reference articles . However , a more accurate literature revision suggests that clone 3 was initially distributed under the name of CHME3 . In this regard , several studies have been published , thus contributing to a more extensive characterization of this cell line . Remarkably , the same cell line has been used in different laboratories with other denominations , i.e. , CHME-5 cells and C13-NJ cells . In view of the fact that `` being now authenticated by ATCC ® '' may imply a wider distribution of the cells , we aimed at reviewing data obtained with the human microglia cell line clone 3 , making the readers aware of this complicated nomenclature . In addition , we also included original data , generated in our laboratory with the HMC3 ( ATCC ® CRL-3304 ) cells , providing information on the current state of the culture together with supplementary details on the culturing procedures to obtain and maintain viable cells .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Microglia , unique myeloid cells residing in the brain parenchyma ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"represent the first line of immune defense within the central nervous system .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"In addition to their immune functions ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"microglial cells play an important role in other cerebral processes ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"including the regulation of synaptic architecture and neurogenesis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Chronic microglial activation is regarded as detrimental ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"and it is considered a pathogenic mechanism common to several neurological disorders .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Microglial activation and function have been extensively studied in rodent experimental models ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"whereas the characterization of human cells has been limited due to the restricted availability of primary sources of human microglia .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"To overcome this problem , human immortalized microglial cell lines have been developed .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"The human microglial clone 3 cell line ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"HMC3 , was established in 1995 ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"through SV40-dependent immortalization of human embryonic microglial cells .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}, {\"segment_text\": \"It has been recently authenticated by the American Type Culture Collection ( ATCC ® ) and distributed under the name of HMC3 ( ATCC ® CRL-3304 ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 14}, {\"segment_text\": \"The HMC3 cells have been used in six research studies ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 15}, {\"segment_text\": \"two of which also indicated by ATCC ® as reference articles .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 16}, {\"segment_text\": \"However , a more accurate literature revision suggests that clone 3 was initially distributed under the name of CHME3 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 17}, {\"segment_text\": \"In this regard , several studies have been published ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 18}, {\"segment_text\": \"thus contributing to a more extensive characterization of this cell line .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 19}, {\"segment_text\": \"Remarkably , the same cell line has been used in different laboratories with other denominations ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"i.e. , CHME-5 cells and C13-NJ cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"In view of the fact that `` being now authenticated by ATCC ® '' may imply a wider distribution of the cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"we aimed at reviewing data obtained with the human microglia cell line clone 3 ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 23}, {\"segment_text\": \"making the readers aware of this complicated nomenclature .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 24}, {\"segment_text\": \"In addition , we also included original data ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 25}, {\"segment_text\": \"generated in our laboratory with the HMC3 ( ATCC ® CRL-3304 ) cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 26}, {\"segment_text\": \"providing information on the current state of the culture together with supplementary details on the culturing procedures to obtain and maintain viable cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 27}]}"}]}
{"paper_id": "9223fd6478822761845291fe2ac429ca6ddbb45a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAssociation of targeted multiplex PCR with resequencing microarray for the detection of multiple respiratory pathogens . Front . Microbiol . 6:532 . A large number of viral and bacterial organisms are responsible for community-acquired pneumonia ( CAP ) which contributes to substantial burden on health management . A new resequencing microarray ( RPM-IVDC1 ) associated with targeted multiplex PCR was recently developed and validated for multiple respiratory viruses detection and discrimination . In this study , we evaluated the capability of RPM-IVDC1 for simultaneous identification of multiple viral and bacterial organisms . The nasopharyngeal aspirates ( NPAs ) of 110 consecutive CAP patients , aged from 1 month to 96 years old , were collected from five distinct general hospitals in Beijing during 1-year period . The samples were subjected to the RPM-IVDC1 established protocol as compared to a real-time PCR ( qRT-PCR ) , which was used as standard . The results of virus detection were consistent with those previously described . A total of 37 of Streptococcus pneumoniae , 14 of Haemophilus influenzae , 10 of Mycoplasma pneumoniae , two of Klebsiella pneumoniae and one of Moraxella catarrhalis were detected by RPM-IVDC1 . The sensitivities and specificities were compared with those of qRT-PCR for S. pneumoniae ( 100 , 100 % , respectively ) , H. influenzae ( 92.3 , 97.9 % , respectively ) , M. pneumoniae ( 69.2 , 99.0 % , respectively ) , K. pneumoniae ( 100 , 100 % , respectively ) , and M. catarrhalis ( 100 , 100 % , respectively ) . Additional 22 of Streptococcus spp. , 24 of Haemophilus spp. and 16 of Neisseria spp. were identified . In addition , methicillin-resistant and carbapenemases allele were also found in nine of Staphylococcus spp. and one of K. pneumoniae , respectively . These results demonstrated the capability of RPM-IVDC1 for simultaneous detection of broad-spectrum respiratory pathogens in complex backgrounds and the advantage of accessing to the actual sequences , showing great potential use of epidemic outbreak investigation . The detection results should be carefully interpreted when introducing this technique in the clinical diagnostics .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Association of targeted multiplex PCR with resequencing microarray for the detection of multiple respiratory pathogens .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Front .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 2}, {\"segment_text\": \"Microbiol .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 3}, {\"segment_text\": \"6:532 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 4}, {\"segment_text\": \"A large number of viral and bacterial organisms are responsible for community-acquired pneumonia ( CAP ) which contributes to substantial burden on health management .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"A new resequencing microarray ( RPM-IVDC1 ) associated with targeted multiplex PCR was recently developed and validated for multiple respiratory viruses detection and discrimination .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"In this study , we evaluated the capability of RPM-IVDC1 for simultaneous identification of multiple viral and bacterial organisms .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"The nasopharyngeal aspirates ( NPAs ) of 110 consecutive CAP patients ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"aged from 1 month to 96 years old ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"were collected from five distinct general hospitals in Beijing during 1-year period .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"The samples were subjected to the RPM-IVDC1 established protocol as compared to a real-time PCR ( qRT-PCR ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"which was used as standard .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"The results of virus detection were consistent with those previously described .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"A total of 37 of Streptococcus pneumoniae ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"14 of Haemophilus influenzae , 10 of Mycoplasma pneumoniae ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"two of Klebsiella pneumoniae and one of Moraxella catarrhalis were detected by RPM-IVDC1 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"The sensitivities and specificities were compared with those of qRT-PCR for S. pneumoniae ( 100 , 100 % , respectively ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"H. influenzae ( 92.3 , 97.9 % , respectively ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"M. pneumoniae ( 69.2 , 99.0 % , respectively ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"K. pneumoniae ( 100 , 100 % , respectively ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"and M. catarrhalis ( 100 , 100 % , respectively ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"Additional 22 of Streptococcus spp. ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"24 of Haemophilus spp. and 16 of Neisseria spp. were identified .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"In addition , methicillin-resistant and carbapenemases allele were also found in nine of Staphylococcus spp. and one of K. pneumoniae , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}, {\"segment_text\": \"These results demonstrated the capability of RPM-IVDC1 for simultaneous detection of broad-spectrum respiratory pathogens in complex backgrounds and the advantage of accessing to the actual sequences ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 25}, {\"segment_text\": \"showing great potential use of epidemic outbreak investigation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 26}, {\"segment_text\": \"The detection results should be carefully interpreted when introducing this technique in the clinical diagnostics .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 27}]}"}]}
{"paper_id": "b3ffd5f3aca72237efedb53065b9469445893991", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nHighlights d Intranasal but not subcutaneous vaccination protects mice from pathogenic human CoVs d Protection is mediated by airway memory CD4 + T cells d IFN-g produced by airway memory CD4 + T cells is required for protection d A conserved epitope in SARS-CoV and MERS-CoV induces cross-reactive T cell responses SUMMARY MERS-CoV-have crossed species to cause severe human respiratory disease . Here , we showed that induction of airway memory CD4 + T cells specific for a conserved epitope shared by SARS-CoV and MERS-CoV is a potential strategy for developing pancoronavirus vaccines . Airway memory CD4 + T cells differed phenotypically and functionally from lungderived cells and were crucial for protection against both CoVs in mice . Protection was dependent on interferon-g and required early induction of robust innate and virus-specific CD8 + T cell responses . The conserved epitope was also recognized in SARS-CoV-and MERS-CoV-infected human leukocyte antigen DR2 and DR3 transgenic mice , indicating potential relevance in human populations . Additionally , this epitope was cross-protective between human and bat CoVs , the progenitors for many human CoVs . Vaccine strategies that induce airway memory CD4 + T cells targeting conserved epitopes might have broad applicability in the context of new CoVs and other respiratory virus outbreaks .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Highlights d Intranasal but not subcutaneous vaccination protects mice from pathogenic human CoVs d Protection is mediated by airway memory CD4 + T cells d IFN-g produced by airway memory CD4 + T cells is required for protection d A conserved epitope in SARS-CoV and MERS-CoV induces cross-reactive T cell responses SUMMARY\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"MERS-CoV-have crossed species to cause severe human respiratory disease .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Here , we showed that induction of airway memory CD4 + T cells specific for a conserved epitope shared by SARS-CoV and MERS-CoV is a potential strategy for developing pancoronavirus vaccines .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"Airway memory CD4 + T cells differed phenotypically and functionally from lungderived cells and were crucial for protection against both CoVs in mice .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 4}, {\"segment_text\": \"Protection was dependent on interferon-g and required early induction of robust innate and virus-specific CD8 + T cell responses .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"The conserved epitope was also recognized in SARS-CoV-and MERS-CoV-infected human leukocyte antigen DR2 and DR3 transgenic mice ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"indicating potential relevance in human populations .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"Additionally , this epitope was cross-protective between human and bat CoVs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"the progenitors for many human CoVs .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Vaccine strategies that induce airway memory CD4 + T cells targeting conserved epitopes might have broad applicability in the context of new CoVs and other respiratory virus outbreaks .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "148e7a1d9425627f4fd87ded1a79e6208d709d23", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nEncephalitis literally means inflammation of the brain . In general , this inflammation can result from a viral or bacterial infection in the brain itself or alternatively from a secondary autoimmune reaction against an infection or a tumor in the rest of the body . Besides this , encephalitis is present in ( believed autoimmune ) diseases with unknown etiology , such as multiple sclerosis or Rasmussen encephalitis ( RE ) . This article summarizes the existing data on the role of T-cells in the pathogenesis of three types of human encephalitis : RE , paraneoplastic encephalomyelitis , and virus encephalitis . In all of them , T-cells play a major role in disease pathogenesis , mainly mediated by major histocompatiblity complex class I-restricted CD8 + T-lymphocytes .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Encephalitis literally means inflammation of the brain .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"In general , this inflammation can result from a viral or bacterial infection in the brain itself or alternatively from a secondary autoimmune reaction against an infection or a tumor in the rest of the body .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Besides this , encephalitis is present in ( believed autoimmune ) diseases with unknown etiology ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"such as multiple sclerosis or Rasmussen encephalitis ( RE ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"This article summarizes the existing data on the role of T-cells in the pathogenesis of three types of human encephalitis : RE ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"paraneoplastic encephalomyelitis , and virus encephalitis .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"In all of them , T-cells play a major role in disease pathogenesis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"mainly mediated by major histocompatiblity complex class I-restricted CD8 + T-lymphocytes .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}]}"}]}
{"paper_id": "51a16f6110de86c0a245a11b366130d5d7da4137", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nA series of doubly flexible nucleoside analogues were designed based on the acyclic sugar scaffold of acyclovir and the flex-base moiety found in the fleximers . The target compounds were evaluated for their antiviral potential and found to inhibit several coronaviruses . Significantly , compound 2 displayed selective antiviral activity ( CC 50 > 3x EC 50 ) towards human coronavirus ( HCoV ) - NL63 and Middle East respiratory syndrome-coronavirus , but not severe acute respiratory syndrome-coronavirus . In the case of HCoV-NL63 the activity was highly promising with an EC 50 < 10 μM and a CC 50 > 100 μM . As such , these doubly flexible nucleoside analogues are viewed as a novel new class of drug candidates with potential for potent inhibition of coronaviruses .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"A series of doubly flexible nucleoside analogues were designed based on the acyclic sugar scaffold of acyclovir and the flex-base moiety found in the fleximers .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 1}, {\"segment_text\": \"The target compounds were evaluated for their antiviral potential and found to inhibit several coronaviruses .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"Significantly , compound 2 displayed selective antiviral activity ( CC 50 > 3x EC 50 ) towards human coronavirus ( HCoV ) - NL63 and Middle East respiratory syndrome-coronavirus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"but not severe acute respiratory syndrome-coronavirus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"In the case of HCoV-NL63 the activity was highly promising with an EC 50 < 10 μM and a CC 50 > 100 μM .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"As such , these doubly flexible nucleoside analogues are viewed as a novel new class of drug candidates with potential for potent inhibition of coronaviruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}]}"}]}
{"paper_id": "221298016b04a2f16de191343275b930b106b75f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe central nervous system ( CNS ) is a remarkably complex structure that utilizes electrochemical signaling to coordinate activities throughout the entire body . Because the nervous system contains nonreplicative cells , it is postulated that , through evolutionary pressures , this compartment has acquired specialized mechanisms to limit damage . One potential source of damage comes from our immune system , which has the capacity to survey the CNS and periphery for the presence of foreign material . The immune system is equipped with numerous effector mechanisms and can greatly alter the homeostasis and function of the CNS . Degeneration , autoimmunity , and pathogen infection can all result in acute , and sometimes chronic , inflammation within the CNS . Understanding the specialized functionality of innate and adaptive immune cells within the CNS is critical to the design of more efficacious treatments to mitigate CNS inflammatory conditions . Much of our knowledge of CNS-immune interactions stems from seminal studies that have used static and dynamic imaging approaches to visualize inflammatory cells responding to different CNS conditions . This review will focus on how imaging techniques have elevated our understanding of CNS inflammation as well as the exciting prospects that lie ahead as we begin to pursue investigation of the inflamed CNS in real time .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The central nervous system ( CNS ) is a remarkably complex structure that utilizes electrochemical signaling to coordinate activities throughout the entire body .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Because the nervous system contains nonreplicative cells ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"it is postulated that , through evolutionary pressures ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"this compartment has acquired specialized mechanisms to limit damage .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"One potential source of damage comes from our immune system ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"which has the capacity to survey the CNS and periphery for the presence of foreign material .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"The immune system is equipped with numerous effector mechanisms and can greatly alter the homeostasis and function of the CNS .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Degeneration , autoimmunity , and pathogen infection can all result in acute ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"and sometimes chronic , inflammation within the CNS .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"Understanding the specialized functionality of innate and adaptive immune cells within the CNS is critical to the design of more efficacious treatments to mitigate CNS inflammatory conditions .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"Much of our knowledge of CNS-immune interactions stems from seminal studies that have used static and dynamic imaging approaches to visualize inflammatory cells responding to different CNS conditions .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"This review will focus on how imaging techniques have elevated our understanding of CNS inflammation as well as the exciting prospects that lie ahead as we begin to pursue investigation of the inflamed CNS in real time .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}]}"}]}
{"paper_id": "450a282e43d38ff85826f975228d51c650361b56", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe dynamics of disease transmission strongly depends on the properties of the population contact network . Pair-approximation models and individual-based network simulation have been used extensively to model contact networks with nontrivial properties . In this paper , using a continuous time Markov chain , we start from the exact formulation of a simple epidemic model on an arbitrary contact network and rigorously derive and prove some known results that were previously mainly justified based on some biological hypotheses . The main result of the paper is the illustration of the link between graph automorphisms and the process of lumping whereby the number of equations in a system of linear differential equations can be significantly reduced . The main advantage of lumping is that the simplified lumped system is not an approximation of the original system but rather an exact version of this . For a special class of graphs , we show how the lumped system can be obtained by using graph automorphisms . Finally , we discuss the advantages and possible applications of exact epidemic models and lumping .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The dynamics of disease transmission strongly depends on the properties of the population contact network .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Pair-approximation models and individual-based network simulation have been used extensively to model contact networks with nontrivial properties .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"In this paper , using a continuous time Markov chain ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"we start from the exact formulation of a simple epidemic model on an arbitrary contact network and rigorously derive and prove some known results that were previously mainly justified based on some biological hypotheses .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"The main result of the paper is the illustration of the link between graph automorphisms and the process of lumping whereby the number of equations in a system of linear differential equations can be significantly reduced .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"The main advantage of lumping is that the simplified lumped system is not an approximation of the original system but rather an exact version of this .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"For a special class of graphs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"we show how the lumped system can be obtained by using graph automorphisms .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Finally , we discuss the advantages and possible applications of exact epidemic models and lumping .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}]}"}]}
{"paper_id": "8e152f8144e2d2ea5b829aa4b7089a49fa903453", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSevere acute respiratory syndrome ( SARS ) is an infectious disease caused by a newly identified human coronavirus ( SARS-CoV ) . Currently , no effective drug exists to treat SARS-CoV infection . In this study , we investigated whether a panel of commercially available antiviral drugs exhibit in vitro anti-SARS-CoV activity . A drugscreening assay that scores for virus-induced cytopathic effects on cultured cells was used . Tested were 19 clinically approved compounds from several major antiviral pharmacologic classes : nucleoside analogs , interferons , protease inhibitors , reverse transcriptase inhibitors , and neuraminidase inhibitors . Complete inhibition of cytopathic effects of SARS-CoV in culture was observed for interferon subtypes , β-1b , α-n1 , α-n3 , and human leukocyte interferon a . These findings support clinical testing of approved interferons for the treatment of SARS .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Severe acute respiratory syndrome ( SARS ) is an infectious disease caused by a newly identified human coronavirus ( SARS-CoV ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Currently , no effective drug exists to treat SARS-CoV infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"In this study , we investigated whether a panel of commercially available antiviral drugs exhibit in vitro anti-SARS-CoV activity .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"A drugscreening assay that scores for virus-induced cytopathic effects on cultured cells was used .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Tested were 19 clinically approved compounds from several major antiviral pharmacologic classes : nucleoside analogs ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"interferons , protease inhibitors , reverse transcriptase inhibitors , and neuraminidase inhibitors .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Complete inhibition of cytopathic effects of SARS-CoV in culture was observed for interferon subtypes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"β-1b , α-n1 , α-n3 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and human leukocyte interferon a .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"These findings support clinical testing of approved interferons for the treatment of SARS .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "c5b1a042d7828891177203755e2201748eec0a14", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : The Cypriot healthcare system has undergone a number of major transformations since the induction of the Republic of Cyprus in the European Union over 10 years ago . Currently Cyprus is undergoing a major reform , namely the introduction of a primary care driven national healthcare system . The aim of the study was to assess the existing state of training , support , quality , guidelines and infrastructure towards a better healthcare system in Cyprus . Methods : This is a mixed-methods study combining statistical data until October 2016 and workshop discussions delivered in Cyprus in November 2015 . We used anonymised data provided : ( 1a ) by the Cyprus Medical Association of all registered medical doctors up to October 2016 ; ( 1b ) ; by the Ministry of Health ( MoH ) Health Monitoring Unit up to October 2016 ; ( 2 ) during a workshop organised with representatives from the Royal College of Physicians , the European Commission and the Health Insurance Organization . Results : The gender ratio of men over women is disproportionate , with over 85 % of the medical doctors undertaking their training in Greece , Eastern Europe and neighbouring countries , while the current record does not hold a relevant specialty information for 4 out of 10 doctors . The results show lack of statutory inspection systems , application of revalidation principles or implementation of peer-review clinical services on the island . There are eight proposed recommendations made by the workshop participants towards the transformation of the Cypriot healthcare system and the development of the Cyprus Quality Improvement Institute . These are aimed at addressing gaps in quality of care , adherence to clinical guidelines and implementation of audits , development of doctors ' revalidation and peerreview of clinical services , accreditation of service implementation , establishment of a statutory inspection system as well as the set-up of an incentives program as part of the general healthcare system ( GHS ) of Cyprus . Conclusions : Current efforts for the implementation of the new GHS in Cyprus call for adequate training and support of the medical workforce , transparent and safer quality of care provision through the implementation of clinical guidelines and capacity-building infrastructure .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : The Cypriot healthcare system has undergone a number of major transformations since the induction of the Republic of Cyprus in the European Union over 10 years ago .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Currently Cyprus is undergoing a major reform ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"namely the introduction of a primary care driven national healthcare system .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"The aim of the study was to assess the existing state of training ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"support , quality , guidelines and infrastructure towards a better healthcare system in Cyprus .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Methods : This is a mixed-methods study combining statistical data until October 2016 and workshop discussions delivered in Cyprus in November 2015 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"We used anonymised data provided : ( 1a ) by the Cyprus Medical Association of all registered medical doctors up to October 2016 ; ( 1b ) ; by the Ministry of Health ( MoH ) Health Monitoring Unit up to October 2016 ; ( 2 ) during a workshop organised with representatives from the Royal College of Physicians ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"the European Commission and the Health Insurance Organization .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Results : The gender ratio of men over women is disproportionate ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"with over 85 % of the medical doctors undertaking their training in Greece ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"Eastern Europe and neighbouring countries ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"while the current record does not hold a relevant specialty information for 4 out of 10 doctors .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"The results show lack of statutory inspection systems ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"application of revalidation principles or implementation of peer-review clinical services on the island .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"There are eight proposed recommendations made by the workshop participants towards the transformation of the Cypriot healthcare system and the development of the Cyprus Quality Improvement Institute .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"These are aimed at addressing gaps in quality of care ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"adherence to clinical guidelines and implementation of audits ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"development of doctors ' revalidation and peerreview of clinical services ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"accreditation of service implementation , establishment of a statutory inspection system as well as the set-up of an incentives program as part of the general healthcare system ( GHS ) of Cyprus .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"Conclusions : Current efforts for the implementation of the new GHS in Cyprus call for adequate training and support of the medical workforce ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}, {\"segment_text\": \"transparent and safer quality of care provision through the implementation of clinical guidelines and capacity-building infrastructure .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}]}"}]}
{"paper_id": "de37edb6bd7020a8232ed2637ec60b177039f9c8", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground . Animal models suggest that influenza infection favors nasopharyngeal acquisition of pneumococci . We assessed this relationship with influenza and other respiratory viruses in young children . Methods . A case-control study was nested within a prospective cohort study of acute respiratory illness ( ARI ) in Andean children < 3 years of age ( RESPIRA-PERU study ) . Weekly household visits were made to identify ARI and obtain nasal swabs for viral detection using real-time reverse-transcription polymerase chain reaction . Monthly nasopharyngeal ( NP ) samples were obtained to assess pneumococcal colonization . We determined whether specific respiratory viral ARI episodes occurring within the interval between NP samples increased the risk of NP acquisition of new pneumococcal serotypes . Results . A total of 729 children contributed 2128 episodes of observation , including 681 pneumococcal acquisition episodes ( new serotype , not detected in prior sample ) , 1029 nonacquisition episodes ( no colonization or persistent colonization with the same serotype as the prior sample ) , and 418 indeterminate episodes . The risk of pneumococcal acquisition increased following influenza-ARI ( adjusted odds ratio ( AOR ) , 2.19 ; 95 % confidence interval ( CI ) , 1.02-4.69 ) and parainfluenza-ARI ( AOR , 1.86 ; 95 % CI , 1.15-3.01 ) , when compared with episodes without ARI . Other viral infections ( respiratory syncytial virus , human metapneumovirus , human rhinovirus , and adenovirus ) were not associated with acquisition . Conclusions . Influenza and parainfluenza ARIs appeared to facilitate pneumococcal acquisition among young children . As acquisition increases the risk of pneumococcal diseases , these observations are pivotal in our attempts to prevent pneumococcal disease .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Animal models suggest that influenza infection favors nasopharyngeal acquisition of pneumococci .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"We assessed this relationship with influenza and other respiratory viruses in young children .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"Methods .\", \"label\": \"method\", \"decision_reference\": \"other.rule\", \"id\": 4}, {\"segment_text\": \"A case-control study was nested within a prospective cohort study of acute respiratory illness ( ARI ) in Andean children < 3 years of age ( RESPIRA-PERU study ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Weekly household visits were made to identify ARI and obtain nasal swabs for viral detection using real-time reverse-transcription polymerase chain reaction .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Monthly nasopharyngeal ( NP ) samples were obtained to assess pneumococcal colonization .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"We determined whether specific respiratory viral ARI episodes occurring within the interval between NP samples increased the risk of NP acquisition of new pneumococcal serotypes .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Results .\", \"label\": \"finding\", \"decision_reference\": \"other.rule\", \"id\": 9}, {\"segment_text\": \"A total of 729 children contributed 2128 episodes of observation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"including 681 pneumococcal acquisition episodes ( new serotype , not detected in prior sample ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"1029 nonacquisition episodes ( no colonization or persistent colonization with the same serotype as the prior sample ) , and 418 indeterminate episodes .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"The risk of pneumococcal acquisition increased following influenza-ARI ( adjusted odds ratio ( AOR ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"2.19 ; 95 % confidence interval ( CI ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"1.02-4.69 ) and parainfluenza-ARI ( AOR , 1.86 ; 95 % CI , 1.15-3.01 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"when compared with episodes without ARI .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"Other viral infections ( respiratory syncytial virus , human metapneumovirus , human rhinovirus , and adenovirus ) were not associated with acquisition .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"Conclusions .\", \"label\": \"finding\", \"decision_reference\": \"other.rule\", \"id\": 18}, {\"segment_text\": \"Influenza and parainfluenza ARIs appeared to facilitate pneumococcal acquisition among young children .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"As acquisition increases the risk of pneumococcal diseases ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"these observations are pivotal in our attempts to prevent pneumococcal disease .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}]}"}]}
{"paper_id": "3e6e8c56fde177f72cd84a517ad65b95648448eb", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAlrstraet -- Five conventionally kept calves aged between 17 and 24 days were experimentally infected with bovine respiratory syncytial virus ( BRSV ) by aerosol in order to mimic the natural infection route . The calves were killed and autopsies performed 7 days after the first virus challenge . The BRSV isolate used induced tracheitis , bronchitis and atelectasis in infected calves . The only virus which could be isolated from the lungs of the calves was BRSV . In addition , Mycoplasma bovirhinis was isolated from the lungs or/and trachea of two calves . The clinical and histopathological findings , as well as the detection of BRSV antigens by immunofluorescence in the epithelial cells of lung and trachea , and the reisolation of the virus from bronchoalveolar lavage fluids of all inoculated calves , provided confirmation of successful infection with BRSV .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Alrstraet -- Five conventionally kept calves aged between 17 and 24 days were experimentally infected with bovine respiratory syncytial virus ( BRSV ) by aerosol in order to mimic the natural infection route .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The calves were killed and autopsies performed 7 days after the first virus challenge .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"The BRSV isolate used induced tracheitis ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"bronchitis and atelectasis in infected calves .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"The only virus which could be isolated from the lungs of the calves was BRSV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"In addition , Mycoplasma bovirhinis was isolated from the lungs or/and trachea of two calves .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"The clinical and histopathological findings ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"as well as the detection of BRSV antigens by immunofluorescence in the epithelial cells of lung and trachea ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and the reisolation of the virus from bronchoalveolar lavage fluids of all inoculated calves ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"provided confirmation of successful infection with BRSV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "95e99eed4e794ba4370f856d066c8d7a1910bc46", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCoronaviruses are pathogens with a serious impact on human and animal health . They mostly cause enteric or respiratory disease , which can be severe and life threatening , e.g. , in the case of the zoonotic coronaviruses causing severe acute respiratory syndrome ( SARS ) and Middle East Respiratory Syndrome ( MERS ) in humans . Despite the economic and societal impact of such coronavirus infections , and the likelihood of future outbreaks of additional pathogenic coronaviruses , our options to prevent or treat coronavirus infections remain very limited . This highlights the importance of advancing our knowledge on the replication of these viruses and their interactions with the host . Compared to other + RNA viruses , coronaviruses have an exceptionally large genome and employ a complex genome expression strategy . Next to a role in basic virus replication or virus assembly , many of the coronavirus proteins expressed in the infected cell contribute to the coronavirus-host interplay . For example , by interacting with the host cell to create an optimal environment for coronavirus replication , by altering host gene expression or by counteracting the host 's antiviral defenses . These coronavirus-host interactions are key to viral pathogenesis and will ultimately determine the outcome of infection . Due to the complexity of the coronavirus proteome and replication cycle , our knowledge of host factors involved in coronavirus replication is still in an early stage compared to what is known for some other + RNA viruses . This review summarizes our current understanding of coronavirus-host interactions at the level of the infected cell , with special attention for the assembly and function of the viral RNA-synthesising machinery and the evasion of cellular innate immune responses .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Coronaviruses are pathogens with a serious impact on human and animal health .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"They mostly cause enteric or respiratory disease ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"which can be severe and life threatening ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"e.g. , in the case of the zoonotic coronaviruses causing severe acute respiratory syndrome ( SARS ) and Middle East Respiratory Syndrome ( MERS ) in humans .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Despite the economic and societal impact of such coronavirus infections ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"and the likelihood of future outbreaks of additional pathogenic coronaviruses ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"our options to prevent or treat coronavirus infections remain very limited .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"This highlights the importance of advancing our knowledge on the replication of these viruses and their interactions with the host .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"Compared to other + RNA viruses ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"coronaviruses have an exceptionally large genome and employ a complex genome expression strategy .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"Next to a role in basic virus replication or virus assembly ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"many of the coronavirus proteins expressed in the infected cell contribute to the coronavirus-host interplay .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"For example , by interacting with the host cell to create an optimal environment for coronavirus replication ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}, {\"segment_text\": \"by altering host gene expression or by counteracting the host 's antiviral defenses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 14}, {\"segment_text\": \"These coronavirus-host interactions are key to viral pathogenesis and will ultimately determine the outcome of infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 15}, {\"segment_text\": \"Due to the complexity of the coronavirus proteome and replication cycle ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 16}, {\"segment_text\": \"our knowledge of host factors involved in coronavirus replication is still in an early stage compared to what is known for some other + RNA viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"This review summarizes our current understanding of coronavirus-host interactions at the level of the infected cell ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"with special attention for the assembly and function of the viral RNA-synthesising machinery and the evasion of cellular innate immune responses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}]}"}]}
{"paper_id": "c543901ef5d8b67ab0738043c6e074da5c69ba90", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe development of the complex network graphs permits us to describe any real system such as social , neural , computer or genetic networks by transforming real properties in topological indices ( TIs ) . This work uses Randic 's star networks in order to convert the protein primary structure data in specific topological indices that are used to construct a natural/random protein classification model . The set of natural proteins contains 1046 protein chains selected from the pre-compiled CulledPDB list from PISCES Dunbrack 's Web Lab . This set is characterized by a protein homology of 20 % , a structure resolution of 1.6 Å and R-factor lower than 25 % . The set of random amino acid chains contains 1046 sequences which were generated by Python script according to the same type of residues and average chain length found in the natural set . A new Sequence to Star Networks ( S2SNet ) wxPython GUI application ( with a Graphviz graphics back-end ) was designed by our group in order to transform any character sequence in the following star network topological indices : Shannon entropy of Markov matrices , trace of connectivity matrices , Harary number , Wiener index , Gutman index , Schultz index , Moreau-Broto indices , Balaban distance connectivity index , Kier-Hall connectivity indices and Randic connectivity index . The model was constructed with the General Discriminant Analysis methods from STATISTICA package and gave training/predicting set accuracies of 90.77 % for the forward stepwise model type . In conclusion , this study extends for the first time the classical TIs to protein star network TIs by proposing a model that can predict if a protein/fragment of protein is natural or random using only the amino acid sequence data . This classification can be used in the studies of the protein functions by changing some fragments with random amino acid sequences or to detect the fake amino acid sequences or the errors in proteins . These results promote the use of the S2SNet application not only for protein structure analysis but also for mass spectroscopy , clinical proteomics and imaging , or DNA/RNA structure analysis .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The development of the complex network graphs permits us to describe any real system such as social ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"neural , computer or genetic networks by transforming real properties in topological indices ( TIs ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"This work uses Randic 's star networks in order to convert the protein primary structure data in specific topological indices that are used to construct a natural/random protein classification model .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The set of natural proteins contains 1046 protein chains selected from the pre-compiled CulledPDB list from PISCES Dunbrack 's Web Lab .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"This set is characterized by a protein homology of 20 % ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"a structure resolution of 1.6 Å and R-factor lower than 25 % .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"The set of random amino acid chains contains 1046 sequences which were generated by Python script according to the same type of residues and average chain length found in the natural set .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"A new Sequence to Star Networks ( S2SNet ) wxPython GUI application ( with a Graphviz graphics back-end ) was designed by our group in order to transform any character sequence in the following star network topological indices : Shannon entropy of Markov matrices ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"trace of connectivity matrices , Harary number ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Wiener index , Gutman index ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Schultz index , Moreau-Broto indices ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Balaban distance connectivity index , Kier-Hall connectivity indices and Randic connectivity index .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"The model was constructed with the General Discriminant Analysis methods from STATISTICA package and gave training/predicting set accuracies of 90.77 % for the forward stepwise model type .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"In conclusion , this study extends for the first time the classical TIs to protein star network TIs by proposing a model that can predict if a protein/fragment of protein is natural or random using only the amino acid sequence data .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"This classification can be used in the studies of the protein functions by changing some fragments with random amino acid sequences or to detect the fake amino acid sequences or the errors in proteins .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"These results promote the use of the S2SNet application not only for protein structure analysis but also for mass spectroscopy ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"clinical proteomics and imaging , or DNA/RNA structure analysis .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}]}"}]}
{"paper_id": "968d0b07b0b65a15cedfd2357e3ba9649742836e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Allogeneic hematopoietic stem cell transplantation ( HSCT ) is the only curative treatment available for severe combined immunodeficiency ( SCID ) ; although , there is a high incidence of severe infections and an increased risk of graft-versus host-disease ( GvHD ) with HSCT . Early intervention is a crucial prognostic factor and a HLA-haploidentical parental donor is often available . Haploidentical HSCT protocols utilizing extensively ex vivo T-cell depleted grafts ( CliniMACs system ) have proven efficient in preventing GvHD , but cause a delay in early T-cell recovery that increases the risk of viral infections . Here , we present a novel approach for treating SCID that combines selective depletion of GvHD-inducing alpha/beta ( α/β ) T-cells from the haploidentical HSCT graft with a subsequent donor lymphocyte infusion ( DLI ) enriched for CD45RO + memory T-cells . Results : Our patient was diagnosed with SCID ( T-B + NK + phenotype ) . At 9 months of age , he received a T cell receptor ( TCR ) α/β-cell depleted graft from his haploidentical mother , following a reduced intensity conditioning regimen with no additional GvHD prophylaxis . Engraftment was rapid with complete donor chimerism and no signs of GvHD . However , at 12 weeks post HSCT , the patient was still T-cell lymphopenic with clinical symptoms of multiple severe viral infections . Consequently , therapeutic DLIs were initiated for enhanced anti-viral immunity . The patient was treated with CD45RA + depleted haploidentical maternal donor lymphocytes enriched from unmobilized whole blood , and a total T-cell dose of no more than 25 x10 3 CD3 + cells/kg with > 99.9 % purity of CD3 + CD45RO + memory T-cells was transferred . Following the DLI , a prompt increase in CD3 + CD4 + and CD3 + CD8 + counts was observed with a subsequent clearance of viral infections . No acute or chronic GvHD was observed . Conclusions : Automated depletion of CD45RA + naïve T-cells from unmobilized whole blood is a simple and rapid strategy to provide unmanipulated DLIs , with a potentially broad repertoire of pathogen specific memory T-cells . In the haploidentical setting , CD45RA + depleted DLIs can be safely administered at low T-cell doses for efficient enhancement of viral immunity and limited risk of GvHD . We demonstrate the successful use of this approach following TCR-α/β-cell depleted HSCT for the treatment of SCID .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Allogeneic hematopoietic stem cell transplantation ( HSCT ) is the only curative treatment available for severe combined immunodeficiency ( SCID ) ; although ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"there is a high incidence of severe infections and an increased risk of graft-versus host-disease ( GvHD ) with HSCT .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Early intervention is a crucial prognostic factor and a HLA-haploidentical parental donor is often available .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Haploidentical HSCT protocols utilizing extensively ex vivo T-cell depleted grafts ( CliniMACs system ) have proven efficient in preventing GvHD ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"but cause a delay in early T-cell recovery that increases the risk of viral infections .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Here , we present a novel approach for treating SCID that combines selective depletion of GvHD-inducing alpha/beta ( α/β ) T-cells from the haploidentical HSCT graft with a subsequent donor lymphocyte infusion ( DLI ) enriched for CD45RO + memory T-cells .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"Results : Our patient was diagnosed with SCID ( T-B + NK + phenotype ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"At 9 months of age ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"he received a T cell receptor ( TCR ) α/β-cell depleted graft from his haploidentical mother ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"following a reduced intensity conditioning regimen with no additional GvHD prophylaxis .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"Engraftment was rapid with complete donor chimerism and no signs of GvHD .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"However , at 12 weeks post HSCT ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"the patient was still T-cell lymphopenic with clinical symptoms of multiple severe viral infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"Consequently , therapeutic DLIs were initiated for enhanced anti-viral immunity .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"The patient was treated with CD45RA + depleted haploidentical maternal donor lymphocytes enriched from unmobilized whole blood ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"and a total T-cell dose of no more than 25 x10 3 CD3 + cells/kg with > 99.9 % purity of CD3 + CD45RO + memory T-cells was transferred .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"Following the DLI , a prompt increase in CD3 + CD4 + and CD3 + CD8 + counts was observed with a subsequent clearance of viral infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"No acute or chronic GvHD was observed .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"Conclusions : Automated depletion of CD45RA + naïve T-cells from unmobilized whole blood is a simple and rapid strategy to provide unmanipulated DLIs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"with a potentially broad repertoire of pathogen specific memory T-cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}, {\"segment_text\": \"In the haploidentical setting , CD45RA + depleted DLIs can be safely administered at low T-cell doses for efficient enhancement of viral immunity and limited risk of GvHD .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}, {\"segment_text\": \"We demonstrate the successful use of this approach following TCR-α/β-cell depleted HSCT for the treatment of SCID .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 22}]}"}]}
{"paper_id": "cadffc6860b51e0b7668940b97cc1a55b1b698df", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\npublicly funded repositories , such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source . These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active . ¶ I -24-310-D-20 Urgenze I -24-310-D-20 ¶ Bronchiolite del lattante\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"publicly funded repositories , such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"¶ I -24-310-D-20\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 3}, {\"segment_text\": \"Urgenze I -24-310-D-20 ¶ Bronchiolite del lattante\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 4}]}"}]}
{"paper_id": "367aa0244a4b97d04590b92ba9dba13fccd07ce3", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : The World Health Organization recommends periodic evaluations of influenza surveillance systems to identify areas for improvement and provide evidence of data reliability for policymaking . However , data about the performance of established influenza surveillance systems are limited in Africa , including in the Democratic Republic of Congo ( DRC ) . Methods : We used the Centers for Disease Control and Prevention guidelines to evaluate the performance of the influenza sentinel surveillance system ( ISSS ) in DRC during 2012-2015 . The performance of the system was evaluated using eight surveillance attributes : ( i ) data quality and completeness for key variables , ( ii ) timeliness , ( iii ) representativeness , ( iv ) flexibility , ( v ) simplicity , ( vi ) acceptability , ( vii ) stability and ( viii ) utility . For each attribute , specific indicators were developed and described using quantitative and qualitative methods . Scores for each indicator were as follows : < 60 % weak performance ; 60-79 % moderate performance ; ≥ 80 % good performance . Results : During 2012-2015 , we enrolled and tested 4339 patients with influenza-like illness ( ILI ) and 2869 patients with severe acute respiratory illness ( SARI ) from 11 sentinel sites situated in 5 of 11 provinces . Influenza viruses were detected in 446 ( 10.3 % ) samples from patients with ILI and in 151 ( 5.5 % ) samples from patients with SARI with higher detection during December-May . Data quality and completeness was > 90 % for all evaluated indicators . Other strengths of the system were timeliness , simplicity , stability and utility that scored > 70 % each . Representativeness , flexibility and acceptability had moderate performance . It was reported that the ISSS contributed to : ( i ) a better understanding of the epidemiology , circulating patterns and proportional contribution of influenza virus among patients with ILI or SARI ; ( ii ) acquisition of new key competences related to influenza surveillance and diagnosis ; and ( iii ) continuous education of surveillance staff and clinicians at sentinel sites about influenza . However , due to limited resources no actions were undertaken to mitigate the impact of seasonal influenza epidemics . Conclusions : The system performed overall satisfactorily and provided reliable and timely data about influenza circulation in DRC . The simplicity of the system contributed to its stability . A better use of the available data could be made to inform and promote prevention interventions especially among the most vulnerable groups .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : The World Health Organization recommends periodic evaluations of influenza surveillance systems to identify areas for improvement and provide evidence of data reliability for policymaking .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"However , data about the performance of established influenza surveillance systems are limited in Africa ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"including in the Democratic Republic of Congo ( DRC ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Methods : We used the Centers for Disease Control and Prevention guidelines to evaluate the performance of the influenza sentinel surveillance system ( ISSS ) in DRC during 2012-2015 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"The performance of the system was evaluated using eight surveillance attributes : ( i ) data quality and completeness for key variables ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"( ii ) timeliness , ( iii ) representativeness ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"( iv ) flexibility , ( v ) simplicity ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"( vi ) acceptability , ( vii ) stability and ( viii ) utility .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"For each attribute , specific indicators were developed and described using quantitative and qualitative methods .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Scores for each indicator were as follows : < 60 % weak performance ; 60-79 % moderate performance ; ≥ 80 % good performance .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Results : During 2012-2015 , we enrolled and tested 4339 patients with influenza-like illness ( ILI ) and 2869 patients with severe acute respiratory illness ( SARI ) from 11 sentinel sites situated in 5 of 11 provinces .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Influenza viruses were detected in 446 ( 10.3 % ) samples from patients with ILI and in 151 ( 5.5 % ) samples from patients with SARI with higher detection during December-May .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Data quality and completeness was > 90 % for all evaluated indicators .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"Other strengths of the system were timeliness ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"simplicity , stability and utility that scored > 70 % each .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"Representativeness , flexibility and acceptability had moderate performance .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"It was reported that the ISSS contributed to : ( i ) a better understanding of the epidemiology ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"circulating patterns and proportional contribution of influenza virus among patients with ILI or SARI ; ( ii ) acquisition of new key competences related to influenza surveillance and diagnosis ; and ( iii ) continuous education of surveillance staff and clinicians at sentinel sites about influenza .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"However , due to limited resources no actions were undertaken to mitigate the impact of seasonal influenza epidemics .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"Conclusions : The system performed overall satisfactorily and provided reliable and timely data about influenza circulation in DRC .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"The simplicity of the system contributed to its stability .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}, {\"segment_text\": \"A better use of the available data could be made to inform and promote prevention interventions especially among the most vulnerable groups .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 22}]}"}]}
{"paper_id": "a63e10c460821fd20aa9f58b6d7f4634b05b16ce", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAcute respiratory infections are a major cause of morbidity in children both in developed and developing countries . A wide range of respiratory viruses , including respiratory syncytial virus ( RSV ) , influenza A and B viruses , parainfluenza viruses ( PIVs ) , adenovirus , rhinovirus ( HRV ) , have repeatedly been detected in acute lower respiratory tract infections ( LRTI ) in children in the past decades . However , in the last ten years thanks to progress in molecular technologies , newly discovered viruses have been identified including human Metapneumovirus ( hMPV ) , coronaviruses NL63 ( HcoV-NL63 ) and HKU1 ( HcoV-HKU1 ) , human Bocavirus ( HBoV ) , new enterovirus ( HEV ) , parechovirus ( HpeV ) and rhinovirus ( HRV ) strains , polyomaviruses WU ( WUPyV ) and KI ( KIPyV ) and the pandemic H1N1v influenza A virus . These discoveries have heavily modified previous knowledge on respiratory infections mainly highlighting that pediatric population is exposed to a variety of viruses with similar seasonal patterns . In this context establishing a causal link between a newly identified virus and the disease as well as an association between mixed infections and an increase in disease severity can be challenging . This review will present an overview of newly recognized as well as the main emerging respiratory viruses and seek to focus on the their contribution to infection and co-infection in LRTIs in childhood .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Acute respiratory infections are a major cause of morbidity in children both in developed and developing countries .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"A wide range of respiratory viruses ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"including respiratory syncytial virus ( RSV ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"influenza A and B viruses ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"parainfluenza viruses ( PIVs ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"adenovirus , rhinovirus ( HRV ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"have repeatedly been detected in acute lower respiratory tract infections ( LRTI ) in children in the past decades .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"However , in the last ten years thanks to progress in molecular technologies ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"newly discovered viruses have been identified including human Metapneumovirus ( hMPV ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"coronaviruses NL63 ( HcoV-NL63 ) and HKU1 ( HcoV-HKU1 ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"human Bocavirus ( HBoV ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"new enterovirus ( HEV ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"parechovirus ( HpeV ) and rhinovirus ( HRV ) strains ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 13}, {\"segment_text\": \"polyomaviruses WU ( WUPyV ) and KI ( KIPyV ) and the pandemic H1N1v influenza A virus .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 14}, {\"segment_text\": \"These discoveries have heavily modified previous knowledge on respiratory infections mainly highlighting that pediatric population is exposed to a variety of viruses with similar seasonal patterns .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 15}, {\"segment_text\": \"In this context establishing a causal link between a newly identified virus and the disease as well as an association between mixed infections and an increase in disease severity can be challenging .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"This review will present an overview of newly recognized as well as the main emerging respiratory viruses and seek to focus on the their contribution to infection and co-infection in LRTIs in childhood .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "fc131dc2b4872ee6c3cdd325739368c4e47e242b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nHundreds of thousands of dogs are housed in kennels worldwide , yet there are no standard protocols for assessing the welfare of dogs in these environments . Animal science is focusing increasingly on the importance of animal-based measures for determining welfare states , and those measures that have been used with kennelled dogs are reviewed in this paper with particular focus on their validity and practicality . From a physiological standpoint , studies using cortisol , heart rate and heart rate variability , temperature changes , and immune function are discussed . Behavioural measures are also of great relevance when addressing canine welfare , thus studies on fear and anxiety behaviours , abnormal behaviours like stereotypies , as well as responses to strangers and novel objects are reviewed . Finally , a limited number of studies attempting to use cognitive bias and learning ability are also mentioned as cognitive measures . The literature to date provides a strong background for which measures may be useful in determining the welfare of kennelled canines , however more research is needed to further assess the value of using these methods , particularly in regard to the large degree of individual differences that exist between dogs .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Hundreds of thousands of dogs are housed in kennels worldwide ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"yet there are no standard protocols for assessing the welfare of dogs in these environments .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Animal science is focusing increasingly on the importance of animal-based measures for determining welfare states ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"and those measures that have been used with kennelled dogs are reviewed in this paper with particular focus on their validity and practicality .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"From a physiological standpoint , studies using cortisol ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"heart rate and heart rate variability ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"temperature changes , and immune function are discussed .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Behavioural measures are also of great relevance when addressing canine welfare ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"thus studies on fear and anxiety behaviours ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"abnormal behaviours like stereotypies , as well as responses to strangers and novel objects are reviewed .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"Finally , a limited number of studies attempting to use cognitive bias and learning ability are also mentioned as cognitive measures .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"The literature to date provides a strong background for which measures may be useful in determining the welfare of kennelled canines ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"however more research is needed to further assess the value of using these methods ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"particularly in regard to the large degree of individual differences that exist between dogs .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}]}"}]}
{"paper_id": "54c3a8137f74c923d699e4bd55344b88264778ca", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nFeatures of homologous relationship of proteins can provide us a general picture of protein universe , assist protein design and analysis , and further our comprehension of the evolution of organisms . Here we carried out a study of the evolution of protein molecules by investigating homologous relationships among residue segments . The motive was to identify detailed topological features of homologous relationships for short residue segments in the whole protein universe . Based on the data of a large number of non-redundant proteins , the universe of non-membrane polypeptide was analyzed by considering both residue mutations and structural conservation . By connecting homologous segments with edges , we obtained a homologous relationship network of the whole universe of short residue segments , which we named the graph of polypeptide relationships ( GPR ) . Since the network is extremely complicated for topological transitions , to obtain an in-depth understanding , only subgraphs composed of vital nodes of the GPR were analyzed . Such analysis of vital subgraphs of the GPR revealed a donut-shaped fingerprint . Utilization of this topological feature revealed the switch sites ( where the beginning of exposure of previously hidden `` hot spots '' of fibril-forming happens , in consequence a further opportunity for protein aggregation is provided ; 188-202 ) of the conformational conversion of the normal a-helix-rich prion protein PrP C to the b-sheet-rich PrP Sc that is thought to be responsible for a group of fatal neurodegenerative diseases , transmissible spongiform encephalopathies . Efforts in analyzing other proteins related to various conformational diseases are also introduced .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Features of homologous relationship of proteins can provide us a general picture of protein universe ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"assist protein design and analysis ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"and further our comprehension of the evolution of organisms .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Here we carried out a study of the evolution of protein molecules by investigating homologous relationships among residue segments .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"The motive was to identify detailed topological features of homologous relationships for short residue segments in the whole protein universe .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Based on the data of a large number of non-redundant proteins ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"the universe of non-membrane polypeptide was analyzed by considering both residue mutations and structural conservation .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"By connecting homologous segments with edges ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"we obtained a homologous relationship network of the whole universe of short residue segments ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"which we named the graph of polypeptide relationships ( GPR ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Since the network is extremely complicated for topological transitions ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"to obtain an in-depth understanding ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"only subgraphs composed of vital nodes of the GPR were analyzed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Such analysis of vital subgraphs of the GPR revealed a donut-shaped fingerprint .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Utilization of this topological feature revealed the switch sites ( where the beginning of exposure of previously hidden `` hot spots '' of fibril-forming happens , in consequence a further opportunity for protein aggregation is provided ; 188-202 ) of the conformational conversion of the normal a-helix-rich prion protein PrP C to the b-sheet-rich PrP Sc that is thought to be responsible for a group of fatal neurodegenerative diseases , transmissible spongiform encephalopathies .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Efforts in analyzing other proteins related to various conformational diseases are also introduced .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "4b735ca93a77a4443a12ef137288760636db5b41", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nWe describe an atypical presentation of severe acute respiratory syndrome ( SARS ) in a geriatric patient with multiple coexisting conditions . Interpretation of radiographic changes was confounded by cardiac failure , with resolution of fever causing delayed diagnosis and a cluster of cases . SARS should be considered even if a contact history is unavailable , during an ongoing outbreak .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"We describe an atypical presentation of severe acute respiratory syndrome ( SARS ) in a geriatric patient with multiple coexisting conditions .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Interpretation of radiographic changes was confounded by cardiac failure ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"with resolution of fever causing delayed diagnosis and a cluster of cases .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"SARS should be considered even if a contact history is unavailable , during an ongoing outbreak .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}]}"}]}
{"paper_id": "f071dcbf396ad4171f3984d42f08291385ea9cf7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe current scenario regarding the widespread Zika virus ( ZIKV ) has resulted in numerous diagnostic studies , specifically in South America and in locations where there is frequent entry of travelers returning from ZIKV-affected areas , including pregnant women with or without clinical symptoms of ZIKV infection . The World Health Organization , WHO , announced that millions of cases of ZIKV are likely to occur in the USA in the near future . This situation has created an alarming public health emergency of international concern requiring the detection of this life-threatening viral candidate due to increased cases of newborn microcephaly associated with ZIKV infection . Hence , this review reports possible methods and strategies for the fast and reliable detection of ZIKV with particular emphasis on current updates , knowledge , and new hypotheses that might be helpful for medical professionals in poor and developing countries that urgently need to address this problem . In particular , we emphasize liposome-based biosensors . Although these biosensors are currently among the less popular tools for human disease detection , they have become useful tools for the screening and detection of pathogenic bacteria , fungi , and viruses because of their versatile advantageous features compared to other sensing devices . This review summarizes the currently available methods employed for the rapid detection of ZIKV and suggests an innovative approach involving the application of a liposome-based hypothesis for the development of new strategies for ZIKV detection and their use as effective biomedicinal tools .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The current scenario regarding the widespread Zika virus ( ZIKV ) has resulted in numerous diagnostic studies ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"specifically in South America and in locations where there is frequent entry of travelers returning from ZIKV-affected areas ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"including pregnant women with or without clinical symptoms of ZIKV infection .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The World Health Organization , WHO ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"announced that millions of cases of ZIKV are likely to occur in the USA in the near future .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"This situation has created an alarming public health emergency of international concern requiring the detection of this life-threatening viral candidate due to increased cases of newborn microcephaly associated with ZIKV infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Hence , this review reports possible methods and strategies for the fast and reliable detection of ZIKV with particular emphasis on current updates ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"knowledge , and new hypotheses that might be helpful for medical professionals in poor and developing countries that urgently need to address this problem .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"In particular , we emphasize liposome-based biosensors .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Although these biosensors are currently among the less popular tools for human disease detection ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"they have become useful tools for the screening and detection of pathogenic bacteria ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"fungi , and viruses because of their versatile advantageous features compared to other sensing devices .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"This review summarizes the currently available methods employed for the rapid detection of ZIKV and suggests an innovative approach involving the application of a liposome-based hypothesis for the development of new strategies for ZIKV detection and their use as effective biomedicinal tools .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "ab3cd83b4fa77a65b99102d3d9afcfe861bdb2c4", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Pairing up primers to amplify desired targets and avoid undesired cross reactions can be a combinatorial challenge . Effective prediction of specificity and inclusivity from multiplexed primers and TaqMan ® / Luminex ® probes is a critical step in PCR design . Results : Code is described to identify all primer and probe combinations from a list of unpaired , unordered candidates that should produce a product . It predicts and extracts all amplicon sequences in a large sequence database from a list of primers and probes , allowing degenerate bases and user-specified levels of primer-target mismatch tolerance . Amplicons hit by TaqMan ® / Luminex ® probes are indicated , and products may be annotated with gene information from NCBI . Fragment length distributions are calculated to predict electrophoretic gel banding patterns . Simulate _ PCR is the only freely available software that can be run from the command line for high throughput applications which can calculate all products from large lists of primers and probes compared to a large sequence database such as nt . It requires no prior knowledge of how primers should be paired . Degenerate bases are allowed and entire amplicon sequences are extracted and annotated with gene information . Examples are provided for sets of TaqMan ® / Luminex ® PCR signatures predicted to amplify all HIV-1 genomes , all Coronaviridae genomes , and a group of antibiotic resistance genes . The software is a command line perl script freely available as open source .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Pairing up primers to amplify desired targets and avoid undesired cross reactions can be a combinatorial challenge .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Effective prediction of specificity and inclusivity from multiplexed primers and TaqMan ® / Luminex ® probes is a critical step in PCR design .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Results : Code is described to identify all primer and probe combinations from a list of unpaired ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 3}, {\"segment_text\": \"unordered candidates that should produce a product .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 4}, {\"segment_text\": \"It predicts and extracts all amplicon sequences in a large sequence database from a list of primers and probes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"allowing degenerate bases and user-specified levels of primer-target mismatch tolerance .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"Amplicons hit by TaqMan ® / Luminex ® probes are indicated ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"and products may be annotated with gene information from NCBI .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"Fragment length distributions are calculated to predict electrophoretic gel banding patterns .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Simulate _ PCR is the only freely available software that can be run from the command line for high throughput applications which can calculate all products from large lists of primers and probes compared to a large sequence database such as nt .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"It requires no prior knowledge of how primers should be paired .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"Degenerate bases are allowed and entire amplicon sequences are extracted and annotated with gene information .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"Examples are provided for sets of TaqMan ® / Luminex ® PCR signatures predicted to amplify all HIV-1 genomes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"all Coronaviridae genomes , and a group of antibiotic resistance genes .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"The software is a command line perl script freely available as open source .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}]}"}]}
{"paper_id": "aa1ad941b0eb3a752c0ce992440c37f334d34ae7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRabies virus ( RABV ) infection continues to be a global threat to human and animal health , yet no curative therapy has been developed . RNA interference ( RNAi ) therapy , which silences expression of specific target genes , represents a promising approach for treating viral infections in mammalian hosts . We designed six small interfering ( si ) RNAs ( N473 , N580 , N783 , N796 , N799 and N1227 ) that target the conserved region of the RABV challenge virus standard ( CVS ) -11 strain nucleoprotein ( N ) gene . Using a plasmid-based transient expression model , we demonstrated that N796 , N580 and N799 were capable of significantly inhibiting viral replication in vitro and in vivo . These three siRNAs effectively suppressed RABV expression in infected baby hamster kidney-21 ( BHK-21 ) cells , as evidenced by direct immunofluorescence assay , viral titer measurements , real-time PCR , and Western blotting . In addition , liposome-mediated siRNA expression plasmid delivery to RABV-infected mice significantly increased survival , compared to a nonliposome-mediated delivery method . Collectively , our results showed that the three siRNAs , N796 , N580 and N799 , targeting the N gene could potently inhibit RABV CVS-11 reproduction . These siRNAs have the potential to be developed into new and effective prophylactic anti-RABV drugs .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Rabies virus ( RABV ) infection continues to be a global threat to human and animal health ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"yet no curative therapy has been developed .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"RNA interference ( RNAi ) therapy ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"which silences expression of specific target genes ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"represents a promising approach for treating viral infections in mammalian hosts .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"We designed six small interfering ( si ) RNAs ( N473 , N580 , N783 , N796 , N799 and N1227 ) that target the conserved region of the RABV challenge virus standard ( CVS ) -11 strain nucleoprotein ( N ) gene .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Using a plasmid-based transient expression model ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"we demonstrated that N796 , N580 and N799 were capable of significantly inhibiting viral replication in vitro and in vivo .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"These three siRNAs effectively suppressed RABV expression in infected baby hamster kidney-21 ( BHK-21 ) cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"as evidenced by direct immunofluorescence assay ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"viral titer measurements , real-time PCR , and Western blotting .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"In addition , liposome-mediated siRNA expression plasmid delivery to RABV-infected mice significantly increased survival ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"compared to a nonliposome-mediated delivery method .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Collectively , our results showed that the three siRNAs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"N796 , N580 and N799 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"targeting the N gene could potently inhibit RABV CVS-11 reproduction .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"These siRNAs have the potential to be developed into new and effective prophylactic anti-RABV drugs .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}]}"}]}
{"paper_id": "0be2160c6cfc01fe13a42a9a601103694ce58a5f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nHong Kong 's bioinformatics sector is attaining new heights in combination with its economic boom and the predominance of the working-age group in its population . Factors such as a knowledge-based and free-market economy have contributed towards a prominent position on the world map of bioinformatics . In this review , we have considered the educational measures , landmark research activities and the achievements of bioinformatics companies and the role of the Hong Kong government in the establishment of bioinformatics as strength . However , several hurdles remain . New government policies will assist computational biologists to overcome these hurdles and further raise the profile of the field . There is a high expectation that bioinformatics in Hong Kong will be a promising area for the next generation . Algorithms and software tools on computational biology ( 89 , 90 ) Prof. Tang Lei-Han Department of Physics , HKUST Working on unravelling the underlying mechanism of conformational transformations of biopolymers as well as modelling the metabolic network of a biological system ( 91 , 92 ) Prof. , HKBU Hypothetical and computational methods of rebuild gene regulatory networks as well as transcriptional regulatory networks ( 45 , 95 , 96 ) Working on the algorithms and networks of computational molecular biology ( 97 , 98 ) Interdiscip Sci Comput Life Sci ( 2017 ) 9:224-236 233\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Hong Kong 's bioinformatics sector is attaining new heights in combination with its economic boom and the predominance of the working-age group in its population .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Factors such as a knowledge-based and free-market economy have contributed towards a prominent position on the world map of bioinformatics .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"In this review , we have considered the educational measures ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"landmark research activities and the achievements of bioinformatics companies and the role of the Hong Kong government in the establishment of bioinformatics as strength .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"However , several hurdles remain .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"New government policies will assist computational biologists to overcome these hurdles and further raise the profile of the field .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"There is a high expectation that bioinformatics in Hong Kong will be a promising area for the next generation .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"Algorithms and software tools on computational biology ( 89 , 90 ) Prof. Tang Lei-Han Department of Physics ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"HKUST Working on unravelling the underlying mechanism of conformational transformations of biopolymers as well as modelling the metabolic network of a biological system ( 91 , 92 ) Prof. ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"HKBU Hypothetical and computational methods of rebuild gene regulatory networks as well as transcriptional regulatory networks ( 45 , 95 , 96 ) Working on the algorithms and networks of computational molecular biology ( 97 , 98 ) Interdiscip Sci Comput Life Sci ( 2017 ) 9:224-236 233\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "468c4c6661aa11f560cd00a668fa457c473faea7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe objectives of this experiment were to evaluate the effects of alternatives to antibiotic growth promoters ( AGP ) , two group sizes , and their interaction on nursery pig performance to serve as a model for future AGP alternative studies . A 41-d experiment was conducted in a commercial weanto-finish barn ; 1,300 piglets weaned at 21 d of age ( weaned 2 or 4 d prior to experiment ; 6.14 ± 0.18 kg BW ; PIC 1050 sows and multiple sire lines ) were blocked by sire , sex , and weaning date , then assigned to eight treatments : four dietary treatments each evaluated across two group sizes . The four dietary treatments were : negative control ( NC ) , positive control ( PC ; NC + in-feed antibiotics ) , zinc oxide plus a dietary acidifier ( blend of fumaric , citric , lactic , and phosphoric acid ) ( ZA ; NC + ZnO + acid ) , and a Bacillus-based direct-fed-microbial ( DFM ) plus resistant potato starch ( RS ) ( DR ; NC + DFM + RS ) . The two group sizes were 31 or 11 pigs/pen ; floor space was modified so area/pig was equal between the group sizes ( 0.42 m 2 / pig ) . There were 7 pens/diet with 11 pigs/pen and 8 pens/diet with 31 pigs/pen . Data were analyzed as a randomized complete block design with pen as the experimental unit . Diagnostic assessment of oral fluids , serum , and tissue samples was used to characterize health status . Pigs experienced natural challenges of acute diarrhea and septicemia in week 1 and porcine reproductive and respiratory syndrome virus ( PRRSV ) in weeks 4-6 . There was a significant interaction between diet and group size for ADG ( P = 0.012 ) . PC increased ADG in large and small groups ( P < 0.05 ) and ZA increased ADG only in large groups ( P < 0.05 ) . Small groups had improved ADG compared to large groups when fed NC or DR diets ( P < 0.05 ) . Similarly , PC increased ADFI ( P < 0.05 ) . Compared to NC , ZA improved ADFI in large groups only ( P < 0.05 ; diet × group size : P = 0.015 ) . Pigs fed PC had greater G : F than NC ( P < 0.05 ) , and small groups had greater G : F than large groups ( P < 0.05 ) . There was no effect of ZA or DR on G : F. Pigs fed PC required fewer individual medical treatments than NC and pigs fed ZA were intermediate ( P = 0.024 ) . More pigs were removed from large than small groups ( P = 0.049 ) , and there was no effect of diet on removals ( P > 0.10 ) . In conclusion , careful study design , protocol implementation , sample collection , and recording of important information allowed us to characterize the health status of this group of pigs and determine treatment effects on growth performance and morbidity .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The objectives of this experiment were to evaluate the effects of alternatives to antibiotic growth promoters ( AGP ) ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"two group sizes , and their interaction on nursery pig performance to serve as a model for future AGP alternative studies .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"A 41-d experiment was conducted in a commercial weanto-finish barn ; 1,300 piglets weaned at 21 d of age ( weaned 2 or 4 d prior to experiment ; 6.14 ± 0.18 kg BW ; PIC 1050 sows and multiple sire lines ) were blocked by sire ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"sex , and weaning date ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"then assigned to eight treatments : four dietary treatments each evaluated across two group sizes .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"The four dietary treatments were : negative control ( NC ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"positive control ( PC ; NC + in-feed antibiotics ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"zinc oxide plus a dietary acidifier ( blend of fumaric , citric , lactic , and phosphoric acid ) ( ZA ; NC + ZnO + acid ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"and a Bacillus-based direct-fed-microbial ( DFM ) plus resistant potato starch ( RS ) ( DR ; NC + DFM + RS ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"The two group sizes were 31 or 11 pigs/pen ; floor space was modified so area/pig was equal between the group sizes ( 0.42 m 2 / pig ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"There were 7 pens/diet with 11 pigs/pen and 8 pens/diet with 31 pigs/pen .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Data were analyzed as a randomized complete block design with pen as the experimental unit .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"Diagnostic assessment of oral fluids ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"serum , and tissue samples was used to characterize health status .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"Pigs experienced natural challenges of acute diarrhea and septicemia in week 1 and porcine reproductive and respiratory syndrome virus ( PRRSV ) in weeks 4-6 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"There was a significant interaction between diet and group size for ADG ( P = 0.012 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"PC increased ADG in large and small groups ( P < 0.05 ) and ZA increased ADG only in large groups ( P < 0.05 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Small groups had improved ADG compared to large groups when fed NC or DR diets ( P < 0.05 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Similarly , PC increased ADFI ( P < 0.05 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Compared to NC , ZA improved ADFI in large groups only ( P < 0.05 ; diet × group size : P = 0.015 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"Pigs fed PC had greater G : F than NC ( P < 0.05 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"and small groups had greater G : F than large groups ( P < 0.05 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"There was no effect of ZA or DR on G : F. Pigs fed PC required fewer individual medical treatments than NC and pigs fed ZA were intermediate ( P = 0.024 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"More pigs were removed from large than small groups ( P = 0.049 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}, {\"segment_text\": \"and there was no effect of diet on removals ( P > 0.10 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 25}, {\"segment_text\": \"In conclusion , careful study design ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 26}, {\"segment_text\": \"protocol implementation , sample collection ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 27}, {\"segment_text\": \"and recording of important information allowed us to characterize the health status of this group of pigs and determine treatment effects on growth performance and morbidity .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 28}]}"}]}
{"paper_id": "d3a675bfc74c8ebef84c248dca0b8cc05f5b3ce1", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nObjective-To develop a method to perform multiple tests on single nasopharyngeal ( NP ) swab . Study design-We collected a NP swab on children aged 2-12 years with acute sinusitis and processed it for bacterial culture , viruses , cytokine expression , and 16S ribosomal RNA gene sequencing analysis . During the course of the study , we expand the scope of evaluation to include RNA sequencing , which we accomplished by cutting the tip of the swab . Results-Of the 174 children enrolled , 126 ( 72.4 % ) had a positive bacterial culture and 121 ( 69.5 % ) tested positive for a virus . Cytokine measurement , as judged by the adequate levels of a housekeeping enzyme ( GAPDH ) , appeared successful . From the samples used for 16S ribosomal sequencing we recovered , on average , 16,000 sequences per sample , accounting for a total of 2,646 operational taxonomic units across all samples sequenced . Samples used for RNA sequencing had a mean RNA Integrity number of 6.0 . Cutting the tip of the swab did not affect the recovery yield for viruses or bacteria , nor did it affect species richness in microbiome analysis . Conclusion-We describe a minimally invasive sample collection protocol that allows for multiple diagnostic and research investigations in young children . Users may view , print , copy , and download text and data-mine the content in such documents , for the purposes of academic research , subject always to the full Conditions of use :\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Objective-To develop a method to perform multiple tests on single nasopharyngeal ( NP ) swab .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Study design-We collected a NP swab on children aged 2-12 years with acute sinusitis and processed it for bacterial culture ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"viruses , cytokine expression , and 16S ribosomal RNA gene sequencing analysis .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"During the course of the study ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"we expand the scope of evaluation to include RNA sequencing ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"which we accomplished by cutting the tip of the swab .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Results-Of the 174 children enrolled ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"126 ( 72.4 % ) had a positive bacterial culture and 121 ( 69.5 % ) tested positive for a virus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Cytokine measurement , as judged by the adequate levels of a housekeeping enzyme ( GAPDH ) , appeared successful .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"From the samples used for 16S ribosomal sequencing we recovered ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"on average , 16,000 sequences per sample ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"accounting for a total of 2,646 operational taxonomic units across all samples sequenced .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Samples used for RNA sequencing had a mean RNA Integrity number of 6.0 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Cutting the tip of the swab did not affect the recovery yield for viruses or bacteria ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"nor did it affect species richness in microbiome analysis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Conclusion-We describe a minimally invasive sample collection protocol that allows for multiple diagnostic and research investigations in young children .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Users may view , print ,\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 17}, {\"segment_text\": \"copy , and download text and data-mine the content in such documents ,\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 18}, {\"segment_text\": \"for the purposes of academic research ,\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 19}, {\"segment_text\": \"subject always to the full Conditions of use :\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 20}]}"}]}
{"paper_id": "859a588ec3e56087224a3305abba2ef991ad0712", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe complex relationships between the human and animal species have never ceased to evolve since the emergence of the human species and have resulted in a human-animal interface that has promoted the cross-species transmission , emergence and eventual evolution of a plethora of infectious pathogens . Remarkably , most of the characteristics of the human-animal interface-as we know it today-have been established long before the end of our species prehistorical development took place , to be relentlessly shaped throughout the history of our species . More recently , changes affecting the modern human population worldwide as well as their dramatic impact on the global environment have taken domestication , agriculture , urbanization , industrialization , and colonization to unprecedented levels . This has created a unique global multi-faceted humananimal interface , associated with a major epidemiological transition that is accompanied by an unexpected rise of new and emerging infectious diseases . Importantly , these developments are largely paralleled by medical , technological , and scientific progress , continuously spurred by our never-ending combat against pathogens . The human-animal interface has most likely contributed significantly to the evolutionary shaping and historical development of our species . Investment in a better understanding of this human-animal interface will offer humankind a future head-start in the never-ending battle against infectious diseases .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The complex relationships between the human and animal species have never ceased to evolve since the emergence of the human species and have resulted in a human-animal interface that has promoted the cross-species transmission ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"emergence and eventual evolution of a plethora of infectious pathogens .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Remarkably , most of the characteristics of the human-animal interface-as we know it today-have been established long before the end of our species prehistorical development took place ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"to be relentlessly shaped throughout the history of our species .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"More recently , changes affecting the modern human population worldwide as well as their dramatic impact on the global environment have taken domestication ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"agriculture , urbanization , industrialization ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"and colonization to unprecedented levels .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"This has created a unique global multi-faceted humananimal interface ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"associated with a major epidemiological transition that is accompanied by an unexpected rise of new and emerging infectious diseases .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"Importantly , these developments are largely paralleled by medical ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"technological , and scientific progress ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"continuously spurred by our never-ending combat against pathogens .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"The human-animal interface has most likely contributed significantly to the evolutionary shaping and historical development of our species .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Investment in a better understanding of this human-animal interface will offer humankind a future head-start in the never-ending battle against infectious diseases .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "9bbf07c4bf022a0695b79b87cb4299f6a8d18831", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Glycyrrhiza uralensis is one of the most popular medicinal plants in the world and is also widely used in the flavoring of food and tobacco . Due to limited genomic and transcriptomic data , the biosynthetic pathway of glycyrrhizin , the major bioactive compound in G. uralensis , is currently unclear . Identification of candidate genes involved in the glycyrrhizin biosynthetic pathway will significantly contribute to the understanding of the biosynthetic and medicinal chemistry of this compound . We used the 454 GS FLX platform and Titanium regents to produce a substantial expressed sequence tag ( EST ) dataset from the vegetative organs of G. uralensis . A total of 59,219 ESTs with an average read length of 409 bp were generated . 454 ESTs were combined with the 50,666 G. uralensis ESTs in GenBank . The combined ESTs were assembled into 27,229 unique sequences ( 11,694 contigs and 15,535 singletons ) . A total of 20,437 unique gene elements representing approximately 10,000 independent transcripts were annotated using BLAST searches ( e-value ≤ 1e-5 ) against the SwissProt , KEGG , TAIR , Nr and Nt databases . The assembled sequences were annotated with gene names and Gene Ontology ( GO ) terms . With respect to the genes related to glycyrrhizin metabolism , genes encoding 16 enzymes of the 18 total steps of the glycyrrhizin skeleton synthesis pathway were found . To identify novel genes that encode cytochrome P450 enzymes and glycosyltransferases , which are related to glycyrrhizin metabolism , a total of 125 and 172 unigenes were found to be homologous to cytochrome P450s and glycosyltransferases , respectively . The cytochrome P450 candidate genes were classified into 32 CYP families , while the glycosyltransferase candidate genes were classified into 45 categories by GO analysis . Finally , 3 cytochrome P450 enzymes and 6 glycosyltransferases were selected as the candidates most likely to be involved in glycyrrhizin biosynthesis through an organ-specific expression pattern analysis based on real-time PCR . Conclusions : Using the 454 GS FLX platform and Titanium reagents , our study provides a high-quality EST database for G. uralensis . Based on the EST analysis , novel candidate genes related to the secondary metabolite pathway of glycyrrhizin , including novel genes encoding cytochrome P450s and glycosyltransferases , were found . With the assistance of organ-specific expression pattern analysis , 3 unigenes encoding cytochrome P450s and 6 unigenes encoding glycosyltransferases were selected as the candidates most likely to be involved in glycyrrhizin biosynthesis .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Glycyrrhiza uralensis is one of the most popular medicinal plants in the world and is also widely used in the flavoring of food and tobacco .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Due to limited genomic and transcriptomic data ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"the biosynthetic pathway of glycyrrhizin ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"the major bioactive compound in G. uralensis , is currently unclear .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Identification of candidate genes involved in the glycyrrhizin biosynthetic pathway will significantly contribute to the understanding of the biosynthetic and medicinal chemistry of this compound .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"We used the 454 GS FLX platform and Titanium regents to produce a substantial expressed sequence tag ( EST ) dataset from the vegetative organs of G. uralensis .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"A total of 59,219 ESTs with an average read length of 409 bp were generated .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"454 ESTs were combined with the 50,666 G. uralensis ESTs in GenBank .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The combined ESTs were assembled into 27,229 unique sequences ( 11,694 contigs and 15,535 singletons ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"A total of 20,437 unique gene elements representing approximately 10,000 independent transcripts were annotated using BLAST searches ( e-value ≤ 1e-5 ) against the SwissProt ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"KEGG , TAIR , Nr and Nt databases .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"The assembled sequences were annotated with gene names and Gene Ontology ( GO ) terms .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"With respect to the genes related to glycyrrhizin metabolism ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"genes encoding 16 enzymes of the 18 total steps of the glycyrrhizin skeleton synthesis pathway were found .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"To identify novel genes that encode cytochrome P450 enzymes and glycosyltransferases ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 15}, {\"segment_text\": \"which are related to glycyrrhizin metabolism ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 16}, {\"segment_text\": \"a total of 125 and 172 unigenes were found to be homologous to cytochrome P450s and glycosyltransferases , respectively .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 17}, {\"segment_text\": \"The cytochrome P450 candidate genes were classified into 32 CYP families ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 18}, {\"segment_text\": \"while the glycosyltransferase candidate genes were classified into 45 categories by GO analysis .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 19}, {\"segment_text\": \"Finally , 3 cytochrome P450 enzymes and 6 glycosyltransferases were selected as the candidates most likely to be involved in glycyrrhizin biosynthesis through an organ-specific expression pattern analysis based on real-time PCR .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"Conclusions : Using the 454 GS FLX platform and Titanium reagents ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"our study provides a high-quality EST database for G. uralensis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"Based on the EST analysis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"novel candidate genes related to the secondary metabolite pathway of glycyrrhizin ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}, {\"segment_text\": \"including novel genes encoding cytochrome P450s and glycosyltransferases , were found .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 25}, {\"segment_text\": \"With the assistance of organ-specific expression pattern analysis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 26}, {\"segment_text\": \"3 unigenes encoding cytochrome P450s and 6 unigenes encoding glycosyltransferases were selected as the candidates most likely to be involved in glycyrrhizin biosynthesis .\", \"label\": \"finding\", \"decision_reference\": \"\", \"id\": 27}]}"}]}
{"paper_id": "d9e24a56fd02e643de973aab5753dbf7accc1e90", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Due to its great sensitivity , the nucleic acid amplification test ( NAAT ) is widely used for detection of respiratory viruses ( RV ) . However , few reports have described a direct comparison between multiplex RT-PCR assays for RV . The objective of this study was to perform a direct comparison of three multiplex RT-PCR assays for the detection of respiratory viruses . A total of 201 respiratory samples ( 161 nasopharyngeal swab samples and 40 sputum samples ) were tested with three commercial RV assays : Seegene Anyplex II RV16 ( AP ) , LG AdvanSure RV ( AD ) , and Biosewoom Real-Q RV ( RQ ) . The additional tests for the discrepant results were conducted by repeat RV assay or monoplex PCR coupled direct sequencing . Data analysis using percent agreement , kappa , and prevalence-adjusted and bias-adjusted kappa ( PABAK ) values was performed for comparisons among the three RV assays . Results : Of the 201 samples , AP , AD , and RQ detected 105 ( 52.2 % ) , 99 ( 49.3 % ) , and 95 ( 47.3 % ) positive cases respectively . The overall agreement , kappa , and PABAK values for the three assays ranged between 97 % -98 % , 0.76-0.86 , and 0.93-0.96 respectively . The performance of the three assays was very similar , with 94 % -100 % agreement for all comparisons , each virus types . The additional testing of samples showed discrepant results demonstrating that AD assay had the highest rate of concordance with original results . We suggest that all multiplex assay would be suitable for the detection of for respiratory viruses in clinical setting . agreement , nucleic acid amplification test , respiratory virus\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Due to its great sensitivity ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"the nucleic acid amplification test ( NAAT ) is widely used for detection of respiratory viruses ( RV ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"However , few reports have described a direct comparison between multiplex RT-PCR assays for RV .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"The objective of this study was to perform a direct comparison of three multiplex RT-PCR assays for the detection of respiratory viruses .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"A total of 201 respiratory samples ( 161 nasopharyngeal swab samples and 40 sputum samples ) were tested with three commercial RV assays : Seegene Anyplex II RV16 ( AP ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"LG AdvanSure RV ( AD ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"and Biosewoom Real-Q RV ( RQ ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"The additional tests for the discrepant results were conducted by repeat RV assay or monoplex PCR coupled direct sequencing .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Data analysis using percent agreement ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"kappa , and prevalence-adjusted and bias-adjusted kappa ( PABAK ) values was performed for comparisons among the three RV assays .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Results : Of the 201 samples ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"AP , AD , and RQ detected 105 ( 52.2 % ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"99 ( 49.3 % ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"and 95 ( 47.3 % ) positive cases respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"The overall agreement , kappa ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"and PABAK values for the three assays ranged between 97 % -98 % ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"0.76-0.86 , and 0.93-0.96 respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"The performance of the three assays was very similar ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"with 94 % -100 % agreement for all comparisons , each virus types .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"The additional testing of samples\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"showed discrepant results demonstrating that AD assay had the highest rate of concordance with original results .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"We suggest that all multiplex assay would be suitable for the detection of for respiratory viruses in clinical setting .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"agreement , nucleic acid amplification test , respiratory virus\", \"label\": \"finding\", \"decision_reference\": \"other.rule\", \"id\": 23}]}"}]}
{"paper_id": "9ee05def9e9c177e9c22bf4ef9bfcca045572916", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe traditional design of effective vaccines for rapidly-evolving pathogens , such as influenza A virus , has failed to provide broad spectrum and long-lasting protection . With low cost whole genome sequencing technology and powerful computing capabilities , novel computational approaches have demonstrated the potential to facilitate the design of a universal influenza vaccine . However , few studies have integrated computational optimization in the design and discovery of new vaccines . Understanding the potential of computational vaccine design is necessary before these approaches can be implemented on a broad scale . This review summarizes some promising computational approaches under current development , including computationally optimized broadly reactive antigens with consensus sequences , phylogenetic model-based ancestral sequence reconstruction , and immunomics to compute conserved cross-reactive T-cell epitopes . Interactions between virus-host-environment determine the evolvability of the influenza population . We propose that with the development of novel technologies that allow the integration of data sources such as protein structural modeling , host antibody repertoire analysis and advanced phylodynamic modeling , computational approaches will be crucial for the development of a long-lasting universal influenza vaccine . Taken together , computational approaches are powerful and promising tools for the development of a universal influenza vaccine with durable and broad protection .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The traditional design of effective vaccines for rapidly-evolving pathogens ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"such as influenza A virus ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"has failed to provide broad spectrum and long-lasting protection .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"With low cost whole genome sequencing technology and powerful computing capabilities ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"novel computational approaches have demonstrated the potential to facilitate the design of a universal influenza vaccine .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"However , few studies have integrated computational optimization in the design and discovery of new vaccines .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"Understanding the potential of computational vaccine design is necessary before these approaches can be implemented on a broad scale .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"This review summarizes some promising computational approaches under current development ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"including computationally optimized broadly reactive antigens with consensus sequences ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}, {\"segment_text\": \"phylogenetic model-based ancestral sequence reconstruction ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 10}, {\"segment_text\": \"and immunomics to compute conserved cross-reactive T-cell epitopes .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 11}, {\"segment_text\": \"Interactions between virus-host-environment determine the evolvability of the influenza population .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"We propose that with the development of novel technologies that allow the integration of data sources such as protein structural modeling ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"host antibody repertoire analysis and advanced phylodynamic modeling ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"computational approaches will be crucial for the development of a long-lasting universal influenza vaccine .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Taken together , computational approaches are powerful and promising tools for the development of a universal influenza vaccine with durable and broad protection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "b83417aceefa21bf06ba89462781ebe07142a259", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCanine distemper virus ( CDV ) is the causative agent of canine distemper ( CD ) that is a highly contagious , lethal , multisystemic viral disease of receptive carnivores . The prevalence of CDV is a major concern in susceptible animals . Presently , it is unclear whether intragenic recombination can contribute to gene mutations and segment reassortment in the virus . In this study , 25 full-length CDV genome sequences were subjected to phylogenetic and recombinational analyses . The results of phylogenetic analysis , intragenic recombination , and nucleotide selection pressure indicated that mutation and recombination occurred in the six individual genes segment ( H , F , P , N , L , M ) of the CDV genome . The analysis also revealed pronounced genetic diversity in the CDV genome according to the geographically distinct lineages ( genotypes ) , namely Asia-1 , Asia-2 , Asia-3 , Europe , America-1 , and America-2 . The six recombination events were detected using SimPlot and RDP programs . The analysis of selection pressure demonstrated that a majority of the nucleotides in the CDV individual gene were under negative selection . Collectively , these data suggested that homologous recombination acts as a key force driving the genetic diversity and evolution of canine distemper virus .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Canine distemper virus ( CDV ) is the causative agent of canine distemper ( CD ) that is a highly contagious ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"lethal , multisystemic viral disease of receptive carnivores .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The prevalence of CDV is a major concern in susceptible animals .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Presently , it is unclear whether intragenic recombination can contribute to gene mutations and segment reassortment in the virus .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"In this study , 25 full-length CDV genome sequences were subjected to phylogenetic and recombinational analyses .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"The results of phylogenetic analysis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"intragenic recombination , and nucleotide selection pressure indicated that mutation and recombination occurred in the six individual genes segment ( H , F , P , N , L , M ) of the CDV genome .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"The analysis also revealed pronounced genetic diversity in the CDV genome according to the geographically distinct lineages ( genotypes ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"namely Asia-1 , Asia-2 , Asia-3 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Europe , America-1 , and America-2 .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"The six recombination events were detected using SimPlot and RDP programs .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"The analysis of selection pressure demonstrated that a majority of the nucleotides in the CDV individual gene were under negative selection .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"Collectively , these data suggested that homologous recombination acts as a key force driving the genetic diversity and evolution of canine distemper virus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "c6d8ebcd8dfac7fdfa27ca40d2d4f44f24bcd514", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\n• SIS epidemic dynamics is studied in metapopulation networks . • NIR and PIR heterogeneous infection regimes are proposed . • The two regimes both increase the threshold when only infected individuals move . • NIR increases and PIR decreases the threshold if two types of individuals both move . • We also explore the impact of the two regimes on the temporal behavior of epidemic . In this paper , we study epidemic spreading in metapopulation networks wherein each node represents a subpopulation symbolizing a city or an urban area and links connecting nodes correspond to the human traveling routes among cities . Differently from previous studies , we introduce a heterogeneous infection rate to characterize the effect of nodes ' local properties , such as population density , individual health habits , and social conditions , on epidemic infectivity . By means of a mean-field approach and Monte Carlo simulations , we explore how the heterogeneity of the infection rate affects the epidemic dynamics , and find that large fluctuations of the infection rate have a profound impact on the epidemic threshold as well as the temporal behavior of the prevalence above the epidemic threshold . This work can refine our understanding of epidemic spreading in metapopulation networks with the effect of nodes ' local properties .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"• SIS epidemic dynamics is studied in metapopulation networks .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"• NIR and PIR heterogeneous infection regimes are proposed .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"• The two regimes both increase the threshold when only infected individuals move .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"• NIR increases and PIR decreases the threshold if two types of individuals both move .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"• We also explore the impact of the two regimes on the temporal behavior of epidemic .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"In this paper , we study epidemic spreading in metapopulation networks wherein each node represents a subpopulation symbolizing a city or an urban area and links connecting nodes correspond to the human traveling routes among cities .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"Differently from previous studies , we introduce a heterogeneous infection rate to characterize the effect of nodes ' local properties ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"such as population density , individual health habits ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"and social conditions , on epidemic infectivity .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"By means of a mean-field approach and Monte Carlo simulations ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"we explore how the heterogeneity of the infection rate affects the epidemic dynamics ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"and find that large fluctuations of the infection rate have a profound impact on the epidemic threshold as well as the temporal behavior of the prevalence above the epidemic threshold .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"This work can refine our understanding of epidemic spreading in metapopulation networks with the effect of nodes ' local properties .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "ec64f7f7ece2c16fb0a4210295b2527714b11ee0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThis study was designed to determine the therapeutic efficacy and safety of the Shi-cha capsule , a Chinese herbal formula , in the treatment of patients with wind-cold type common cold . In our multi-center , prospective , double-blind , randomized , placebocontrolled , dose-escalation trial , patients with wind-cold type common cold received 0.6 g of Shi-cha capsule plus 0.6 g placebo ( group A ) , 1.2 g of Shi-cha capsule ( group B ) , or 1.2 g placebo ( group C ) , three times daily for 3 days and followed up to 10 days . The primary end point was all symptom duration . The secondary end points were main symptom duration , minor symptom duration , the changes in cumulative symptom score , main symptom score , and minor symptom score 4 days after the treatment , as well as adverse events . A total of 377 patients were recruited and 360 met the inclusive criteria ; 120 patients constituted each treatment group . Compared with patients in group C , patients in groups A and B had significant improvement in the all symptom duration , main symptom duration , minor symptom duration , as well as change from baseline of cumulative symptom score , main symptom score , and minor symptom score at day 4 . The symptom durations and scores showed slight superiority of group B over group A , although these differences were not statistically significant . There were no differences in adverse events . The Shi-cha capsule is efficacious and safe for the treatment of patients with wind-cold type common cold . Larger trials are required to fully assess the benefits and safety of this treatment for common cold .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"This study was designed to determine the therapeutic efficacy and safety of the Shi-cha capsule ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"a Chinese herbal formula , in the treatment of patients with wind-cold type common cold .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"In our multi-center , prospective ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"double-blind , randomized , placebocontrolled ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"dose-escalation trial , patients with wind-cold type common cold received 0.6 g of Shi-cha capsule plus 0.6 g placebo ( group A ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"1.2 g of Shi-cha capsule ( group B ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"or 1.2 g placebo ( group C ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"three times daily for 3 days and followed up to 10 days .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The primary end point was all symptom duration .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"The secondary end points were main symptom duration ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"minor symptom duration , the changes in cumulative symptom score ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"main symptom score , and minor symptom score 4 days after the treatment ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"as well as adverse events .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"A total of 377 patients were recruited and 360 met the inclusive criteria ; 120 patients constituted each treatment group .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"Compared with patients in group C ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"patients in groups A and B had significant improvement in the all symptom duration ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"main symptom duration , minor symptom duration ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"as well as change from baseline of cumulative symptom score ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"main symptom score , and minor symptom score at day 4 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"The symptom durations and scores showed slight superiority of group B over group A ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"although these differences were not statistically significant .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"There were no differences in adverse events .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"The Shi-cha capsule is efficacious and safe for the treatment of patients with wind-cold type common cold .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"Larger trials are required to fully assess the benefits and safety of this treatment for common cold .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}]}"}]}
{"paper_id": "20d1c063410f32eb59b3f3063d506c4888c80bec", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nWe previously identified unusual variants of Moloney and Friend ecotropic mouse gammaretroviruses that have altered host range and are cytopathic in cells of the wild mouse species Mus dunni . Cytopathicity was attributed to different amino acid substitutions at the same critical env residue involved in receptor interaction : S82F in the Moloney variant Spl574 , and S84A in the Friend mouse leukemia virus F-S MLV . Because M. dunni cells carry a variant CAT-1 cell surface virus receptor ( dCAT-1 ) , we examined the role of this receptor variant in cytopathicity and host range . We expressed dCAT-1 or mCAT-1 of NIH 3T3 origin in cells that are not normally infectible with ecotropic MLVs and evaluated the transfectants for susceptibility to virus infection and to virus-induced syncytium formation . The dCAT-1 transfectants , but not the mCAT-1 transfectants , were susceptible to virus-induced cytopathicity , and this cytopathic response was accompanied by the accumulation of unintegrated viral DNA . The dCAT-1 transfectants , however , did not also reproduce the relative resistance of M. dunni cells to Moloney MLV , and the mCAT-1 transfectants did not show the relative resistance of NIH 3T3 cells to Spl574 . Western analysis , use of glycosylation inhibitors and mutagenesis to remove receptor glycosylation sites identified a possible role for cell-specific glycosylation in the modulation of virus entry . Virus entry and virus-induced syncytium formation using the CAT-1 receptor are mediated by a small number of critical amino acid residues in receptor and virus Env . Virus entry is modulated by glycosylation of cellular proteins , and this effect is cell and virus-specific .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"We previously identified unusual variants of Moloney and Friend ecotropic mouse gammaretroviruses that have altered host range and are cytopathic in cells of the wild mouse species Mus dunni .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Cytopathicity was attributed to different amino acid substitutions at the same critical env residue involved in receptor interaction : S82F in the Moloney variant Spl574 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"and S84A in the Friend mouse leukemia virus F-S MLV .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Because M. dunni cells carry a variant CAT-1 cell surface virus receptor ( dCAT-1 ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"we examined the role of this receptor variant in cytopathicity and host range .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"We expressed dCAT-1 or mCAT-1 of NIH 3T3 origin in cells that are not normally infectible with ecotropic MLVs and evaluated the transfectants for susceptibility to virus infection and to virus-induced syncytium formation .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"The dCAT-1 transfectants , but not the mCAT-1 transfectants ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"were susceptible to virus-induced cytopathicity ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and this cytopathic response was accompanied by the accumulation of unintegrated viral DNA .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"The dCAT-1 transfectants , however ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"did not also reproduce the relative resistance of M. dunni cells to Moloney MLV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and the mCAT-1 transfectants did not show the relative resistance of NIH 3T3 cells to Spl574 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Western analysis , use of glycosylation inhibitors and mutagenesis to remove receptor glycosylation sites identified a possible role for cell-specific glycosylation in the modulation of virus entry .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Virus entry and virus-induced syncytium formation using the CAT-1 receptor are mediated by a small number of critical amino acid residues in receptor and virus Env .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Virus entry is modulated by glycosylation of cellular proteins ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"and this effect is cell and virus-specific .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "fadc6206ab3aa16956d146bd426a32e9b6d0f9d8", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIn this article we review important established , newly emergent and potential viral diseases of cats , dogs and rabbits . Topics covered include virus epidemiology , disease pathogenesis , existing and prospective immunoprophylaxis against the viruses . For some feline viruses , notably the immunodeficiency virus , leukaemia virus and peritonitis virus , available vaccines are poorly efficacious but there are good prospects for this . A further challenge for the industry is likely to be due to viruses jumping species and the emergence of more virulent variants of established viruses resulting from mutations as has been the case for the canine parvovirus , coronaviruses and feline calicivirus .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"In this article we review important established ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"newly emergent and potential viral diseases of cats , dogs and rabbits .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Topics covered include virus epidemiology ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"disease pathogenesis , existing and prospective immunoprophylaxis against the viruses .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"For some feline viruses , notably the immunodeficiency virus ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"leukaemia virus and peritonitis virus ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"available vaccines are poorly efficacious but there are good prospects for this .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"A further challenge for the industry is likely to be due to viruses jumping species and the emergence of more virulent variants of established viruses resulting from mutations as has been the case for the canine parvovirus , coronaviruses and feline calicivirus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}]}"}]}
{"paper_id": "9ad61dcfb0a71ebe88c497995cf569eba5e73f8c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Hepatitis C core protein is an attractive target for HCV vaccine aimed to exterminate HCV infected cells . However , although highly immunogenic in natural infection , core appears to have low immunogenicity in experimental settings . We aimed to design an HCV vaccine prototype based on core , and devise immunization regimens that would lead to potent anti-core immune responses which circumvent the immunogenicity limitations earlier observed . Plasmids encoding core with no translation initiation signal ( pCMVcore ) ; with Kozak sequence ( pCMVcoreKozak ) ; and with HCV IRES ( pCMVcoreIRES ) were designed and expressed in a variety of eukaryotic cells . Polyproteins corresponding to HCV 1b amino acids ( aa ) 1-98 and 1-173 were expressed in E. coli . C57BL/6 mice were immunized with four 25 - g doses of pCMVcoreKozak , or pCMV ( I ) . BALB/c mice were immunized with 100 g of either pCMVcore , or pCMVcoreKozak , or pCMVcoreIRES , or empty pCMV ( II ) . Lastly , BALB/c mice were immunized with 20 g of core aa 1-98 in prime and boost , or with 100 g of pCMVcoreKozak in prime and 20 g of core aa 1-98 in boost ( III ) . Antibody response , ( 3 H ) - T-incorporation , and cytokine secretion by core/core peptide-stimulated splenocytes were assessed after each immunization . Results : Plasmids differed in core-expression capacity : mouse fibroblasts transfected with pCMVcore , pCMVcoreIRES and pCMVcoreKozak expressed 0.22 ± 0.18 , 0.83 ± 0.5 , and 13 ± 5 ng core per cell , respectively . Single immunization with highly expressing pCMVcoreKozak induced specific IFN - and IL-2 , and weak antibody response . Single immunization with plasmids directing low levels of core expression induced similar levels of cytokines , strong T-cell proliferation\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Hepatitis C core protein is an attractive target for HCV vaccine aimed to exterminate HCV infected cells .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"However , although highly immunogenic in natural infection ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"core appears to have low immunogenicity in experimental settings .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"We aimed to design an HCV vaccine prototype based on core ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"and devise immunization regimens that would lead to potent anti-core immune responses which circumvent the immunogenicity limitations earlier observed .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Plasmids encoding core with no translation initiation signal ( pCMVcore ) ; with Kozak sequence ( pCMVcoreKozak ) ; and with HCV IRES ( pCMVcoreIRES ) were designed and expressed in a variety of eukaryotic cells .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Polyproteins corresponding to HCV 1b amino acids ( aa ) 1-98 and 1-173 were expressed in E. coli .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"C57BL/6 mice were immunized with four 25 - g doses of pCMVcoreKozak ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"or pCMV ( I ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"BALB/c mice were immunized with 100 g of either pCMVcore ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"or pCMVcoreKozak , or pCMVcoreIRES ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"or empty pCMV ( II ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"Lastly , BALB/c mice were immunized with 20 g of core aa 1-98 in prime and boost ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"or with 100 g of pCMVcoreKozak in prime and 20 g of core aa 1-98 in boost ( III ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"Antibody response , ( 3 H ) - T-incorporation ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 15}, {\"segment_text\": \"and cytokine secretion by core/core peptide-stimulated splenocytes were assessed after each immunization .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 16}, {\"segment_text\": \"Results : Plasmids differed in core-expression capacity : mouse fibroblasts transfected with pCMVcore ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"pCMVcoreIRES and pCMVcoreKozak expressed 0.22 ± 0.18 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"0.83 ± 0.5 , and 13 ± 5 ng core per cell , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Single immunization with highly expressing pCMVcoreKozak induced specific IFN - and IL-2 , and weak antibody response .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"Single immunization with plasmids directing low levels of core expression induced similar levels of cytokines , strong T-cell proliferation\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}]}"}]}
{"paper_id": "c78a152566f57c00668f5a7d4949515f4f3a5883", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nO. is a 37-year-old male with no significant past medical history who presented to the Emergency Department with a one week history of worsening dysphagia and odynophagia . He reported he was usually in good health until the current symptoms began . Scott said that he had been unable to swallow solid foods over the past week , largely due to increasing pain on swallowing , and was now unable to swallow liquids as well . Although he stated that his appetite was unchanged , he estimated a fivepound weight loss over the last week due to poor oral intake . He otherwise denied fever , respiratory or gastrointestinal symptoms , or any other complaints . He takes no medications at home except for rare acetaminophen . He is married , has a twoyear-old son , and works as an attorney . He denied use of tobacco , alcohol , or illicit drugs . Family history was noncontributory . On physical exam , he was afebrile and his vital signs were within normal limits . Cardiovascular , respiratory , abdominal , extremity , and neurologic exam were unremarkable . There was some mild oropharyngeal thrush , palpable bilateral inguinal lymphadenopathy , and a 1 cm painless ulceration on the penile shaft . Laboratory evaluation was unremarkable .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"O. is a 37-year-old male with no significant past medical history who presented to the Emergency Department with a one week history of worsening dysphagia and odynophagia .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"He reported he was usually in good health until the current symptoms began .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Scott said that he had been unable to swallow solid foods over the past week ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"largely due to increasing pain on swallowing ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"and was now unable to swallow liquids as well .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Although he stated that his appetite was unchanged ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"he estimated a fivepound weight loss over the last week due to poor oral intake .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"He otherwise denied fever , respiratory or gastrointestinal symptoms , or any other complaints .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"He takes no medications at home except for rare acetaminophen .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"He is married , has a twoyear-old son ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"and works as an attorney .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"He denied use of tobacco ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"alcohol , or illicit drugs .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}, {\"segment_text\": \"Family history was noncontributory .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 14}, {\"segment_text\": \"On physical exam , he was afebrile and his vital signs were within normal limits .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"Cardiovascular , respiratory , abdominal ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"extremity , and neurologic exam were unremarkable .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"There was some mild oropharyngeal thrush ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"palpable bilateral inguinal lymphadenopathy , and a 1 cm painless ulceration on the penile shaft .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"Laboratory evaluation was unremarkable .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}]}"}]}
{"paper_id": "c3817cf268182b3b6252d8bf70ff39e24581fe11", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBiomolecular NMR now contributes routinely to every step in the development of new chemical entities ahead of clinical trials . The versatility of NMR - from detection of ligand binding over a wide range of affinities and a wide range of drug targets with its wealth of molecular information , to metabolomic profiling , both ex vivo and in vivo - has paved the way for broadly distributed applications in academia and the pharmaceutical industry . Proteomics and initial target selection both benefit from NMR : screenings by NMR identify lead compounds capable of inhibiting protein-protein interactions , still one of the most difficult development tasks in drug discovery . NMR hardware improvements have given access to the microgram domain of phytochemistry , which should lead to the discovery of novel bioactive natural compounds . Steering medicinal chemists through the lead optimisation process by providing detailed information about protein-ligand interactions has led to impressive success in the development of novel drugs . The study of biofluid compositionmetabonomics - provides information about pharmacokinetics and helps toxicological safety assessment in animal model systems . In vivo , magnetic resonance spectroscopy interrogates metabolite distributions in living cells and tissues with increasing precision , which significantly impacts the development of anticancer or neurological disorder therapeutics . An overview of different steps in recent drug discovery is presented to illuminate the links with the most recent advances in NMR methodology .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Biomolecular NMR now contributes routinely to every step in the development of new chemical entities ahead of clinical trials .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"The versatility of NMR - from detection of ligand binding over a wide range of affinities and a wide range of drug targets with its wealth of molecular information ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"to metabolomic profiling , both ex vivo and in vivo - has paved the way for broadly distributed applications in academia and the pharmaceutical industry .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Proteomics and initial target selection both benefit from NMR : screenings by NMR identify lead compounds capable of inhibiting protein-protein interactions ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"still one of the most difficult development tasks in drug discovery .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"NMR hardware improvements have given access to the microgram domain of phytochemistry ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"which should lead to the discovery of novel bioactive natural compounds .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"Steering medicinal chemists through the lead optimisation process by providing detailed information about protein-ligand interactions has led to impressive success in the development of novel drugs .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"The study of biofluid compositionmetabonomics - provides information about pharmacokinetics and helps toxicological safety assessment in animal model systems .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"In vivo , magnetic resonance spectroscopy interrogates metabolite distributions in living cells and tissues with increasing precision ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"which significantly impacts the development of anticancer or neurological disorder therapeutics .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"An overview of different steps in recent drug discovery is presented to illuminate the links with the most recent advances in NMR methodology .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}]}"}]}
{"paper_id": "f2a43da3e565ffb44289385ed3c6a4658dc166c1", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCytokine expression patterns of T cells can be regulated by pre-commitment to stable effector phenotypes , further modification of moderately stable phenotypes , and quantitative changes in cytokine production in response to acute signals . We showed previously that the epidermal growth factor family member Amphiregulin is expressed by T cell receptor-activated mouse CD4 T cells , particularly Th2 cells , and helps eliminate helminth infection . Here we report a detailed analysis of the regulation of Amphiregulin expression by human T cell subsets . Signaling through the T cell receptor induced Amphiregulin expression by most or all T cell subsets in human peripheral blood , including naive and memory CD4 and CD8 T cells , Th1 and Th2 in vitro T cell lines , and subsets of memory CD4 T cells expressing several different chemokine receptors and cytokines . In these different T cell types , Amphiregulin synthesis was inhibited by an antagonist of protein kinase A , a downstream component of the cAMP signaling pathway , and enhanced by ligands that increased cAMP or directly activated protein kinase A. Prostaglandin E2 and adenosine , natural ligands that stimulate adenylyl cyclase activity , also enhanced Amphiregulin synthesis while reducing synthesis of most other cytokines . Thus , in contrast to mouse T cells , Amphiregulin synthesis by human T cells is regulated more by acute signals than precommitment of T cells to a particular cytokine pattern . This may be appropriate for a cytokine more involved in repair than attack functions during most inflammatory responses .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Cytokine expression patterns of T cells can be regulated by pre-commitment to stable effector phenotypes ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"further modification of moderately stable phenotypes ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"and quantitative changes in cytokine production in response to acute signals .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"We showed previously that the epidermal growth factor family member Amphiregulin is expressed by T cell receptor-activated mouse CD4 T cells ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"particularly Th2 cells , and helps eliminate helminth infection .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Here we report a detailed analysis of the regulation of Amphiregulin expression by human T cell subsets .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"Signaling through the T cell receptor induced Amphiregulin expression by most or all T cell subsets in human peripheral blood ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"including naive and memory CD4 and CD8 T cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Th1 and Th2 in vitro T cell lines ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"and subsets of memory CD4 T cells expressing several different chemokine receptors and cytokines .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"In these different T cell types ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Amphiregulin synthesis was inhibited by an antagonist of protein kinase A ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"a downstream component of the cAMP signaling pathway ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"and enhanced by ligands that increased cAMP or directly activated protein kinase A. Prostaglandin E2 and adenosine ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"natural ligands that stimulate adenylyl cyclase activity ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"also enhanced Amphiregulin synthesis while reducing synthesis of most other cytokines .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Thus , in contrast to mouse T cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Amphiregulin synthesis by human T cells is regulated more by acute signals than precommitment of T cells to a particular cytokine pattern .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"This may be appropriate for a cytokine more involved in repair than attack functions during most inflammatory responses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}]}"}]}
{"paper_id": "b31a7e404bc2caa14f6f03c5737ffa19c41995e5", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe 3C-like protease ( 3CL pro ) of severe acute respiratory syndrome associated coronavirus ( SARS-CoV ) is vital for SARS-CoV replication and is a promising drug target . Recombinant 3CL pro was expressed in Pichia pastoris GS115 as a 42 kDa protein that displayed a K m of 15 ± 2 lM with Dabcyl-KTSAVLQSGFRKME-Edans as substrate . Purified 3CL pro was used for inhibition and kinetic assays with seven flavonoid compounds . The IC 50 of six flavonoid compounds were 47-381 lM . Quercetin , epigallocatechin gallate and gallocatechin gallate ( GCG ) displayed good inhibition toward 3CL pro with IC 50 values of 73 , 73 and 47 lM , respectively . GCG showed a competitive inhibition pattern with K i value of 25 ± 1.7 lM . In molecular docking experiments , GCG displayed a binding energy of -14 kcal mol -1 to the active site of 3CL pro and the galloyl moiety at 3-OH position was required for 3CL pro inhibition activity .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The 3C-like protease ( 3CL pro ) of severe acute respiratory syndrome associated coronavirus ( SARS-CoV ) is vital for SARS-CoV replication and is a promising drug target .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Recombinant 3CL pro was expressed in Pichia pastoris GS115 as a 42 kDa protein that displayed a K m of 15 ± 2 lM with Dabcyl-KTSAVLQSGFRKME-Edans as substrate .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"Purified 3CL pro was used for inhibition and kinetic assays with seven flavonoid compounds .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"The IC 50 of six flavonoid compounds were 47-381 lM .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 4}, {\"segment_text\": \"Quercetin , epigallocatechin gallate and gallocatechin gallate ( GCG ) displayed good inhibition toward 3CL pro with IC 50 values of 73 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"73 and 47 lM , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"GCG showed a competitive inhibition pattern with K i value of 25 ± 1.7 lM .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"In molecular docking experiments , GCG displayed a binding energy of -14 kcal mol -1 to the active site of 3CL pro and the galloyl moiety at 3-OH position was required for 3CL pro inhibition activity .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}]}"}]}
{"paper_id": "a74c29bfc488ed46a2bd41117889f82a3af8b426", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAs the rapidly advancing possibilities of biotechnology have outstripped the adaptive capacity of current legal and ethical institutions , a vigorous debate has arisen that considers the boundaries of appropriate use of this technology , particularly when applied to humans . This article examines ethical concerns surrounding the development of markets in a particular form of human genetic engineering in which heterozygotes are fitter than both homozygotes , a condition known as heterozygous advantage . To begin , we present a generalized model of the condition , illuminated by the application to sickle-cell anemia . Next , we propose a typology of related markets , some of which are currently functioning with available products and services , and others that are widely viewed as imminent . We suggest the manner in which perverse incentives may arise for firms that market genetic intervention in circumstances where heterozygous advantage is possible . Finally , we propose that this misalignment of incentives with social welfare has arisen from both ill-conceived market intervention where markets are capable of achieving efficient outcomes and the lack of market intervention where markets have failed . We offer specific legal and regulatory approaches for reform .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"As the rapidly advancing possibilities of biotechnology have outstripped the adaptive capacity of current legal and ethical institutions ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"a vigorous debate has arisen that considers the boundaries of appropriate use of this technology ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"particularly when applied to humans .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"This article examines ethical concerns surrounding the development of markets in a particular form of human genetic engineering in which heterozygotes are fitter than both homozygotes ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"a condition known as heterozygous advantage .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"To begin , we present a generalized model of the condition ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"illuminated by the application to sickle-cell anemia .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Next , we propose a typology of related markets ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"some of which are currently functioning with available products and services ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"and others that are widely viewed as imminent .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"We suggest the manner in which perverse incentives may arise for firms that market genetic intervention in circumstances where heterozygous advantage is possible .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Finally , we propose that this misalignment of incentives with social welfare has arisen from both ill-conceived market intervention where markets are capable of achieving efficient outcomes and the lack of market intervention where markets have failed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"We offer specific legal and regulatory approaches for reform .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "80d48ddb6b4516ab797e00caac070c1d3704343e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nEthnopharmacological relevance : Yu Ping Feng San ( YPFS , in Chinese : Jade Windscreen Powder ) , a wellknown traditional Chinese medicine , is commonly used to cure the diseases of respiratory systems and immune systems . Aim of the study : A selective and sensitive high-performance liquid chromatography coupled with mass spectrometry method ( HPLC-MS ) was developed and validated for simultaneous quantification of cycloastragenol , formononetin , calycosin , 4 0 - O-b-glucopyranosyl-5-O-methylvisamminol ( GMV ) and cimifugin in rat plasma after oral administration of Yu Ping Feng San decoction . Materials and methods : Plasma samples were extracted via solid-phase extraction ( SPE ) , separated on a Zorbax SB-C18 column , detected by single quadruple mass spectrometry with an electrospray ionization interface , and quantified using selected ion monitoring mode . The current SPE-HPLC-MS assay was validated for linearity , intra-day and inter-day precisions , accuracy , extraction recovery and stability . The method was applied to a comparative pharmacokinetic study after administration of Yu Ping Feng San to rats at different doses ( 10 , 20 and 40 g/kg ) . Results : The calibration curves were linear over the ranges 0.50-50 ng/mL and 17.36-1736 ng/mL . Intra-and inter-day precisions ( relative standard deviations ) were from 0.45 % to 10.95 % , and accuracy ( relative recovery ) from 95 % to 115 % . The extraction recoveries were greater than 88.42 % for all analytes . Dose-dependence was shown for some constituents in the drug concentration-time profiles . Among all the active ingredients detected , cimifugin had the highest blood concentration ( 881-1510 ng/mL ) , and cycloastragenol had the longest retention time in the rat body ( 15.06-20.44 h ) . Conclusion : This analytical method is a selective , sensitive , precise , accurate , and reliable assay for simultaneous determination of cycloastragenol , calycosin , formononetin , GMV , and cimifugin in rat plasma .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Ethnopharmacological relevance : Yu Ping Feng San ( YPFS , in Chinese : Jade Windscreen Powder ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"a wellknown traditional Chinese medicine ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"is commonly used to cure the diseases of respiratory systems and immune systems .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Aim of the study : A selective and sensitive high-performance liquid chromatography coupled with mass spectrometry method ( HPLC-MS ) was developed and validated for simultaneous quantification of cycloastragenol ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"formononetin , calycosin , 4 0 - O-b-glucopyranosyl-5-O-methylvisamminol ( GMV ) and cimifugin in rat plasma after oral administration of Yu Ping Feng San decoction .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Materials and methods : Plasma samples were extracted via solid-phase extraction ( SPE ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"separated on a Zorbax SB-C18 column ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"detected by single quadruple mass spectrometry with an electrospray ionization interface ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"and quantified using selected ion monitoring mode .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"The current SPE-HPLC-MS assay was validated for linearity ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"intra-day and inter-day precisions , accuracy , extraction recovery and stability .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"The method was applied to a comparative pharmacokinetic study after administration of Yu Ping Feng San to rats at different doses ( 10 , 20 and 40 g/kg ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"Results : The calibration curves were linear over the ranges 0.50-50 ng/mL and 17.36-1736 ng/mL .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"Intra-and inter-day precisions ( relative standard deviations ) were from 0.45 % to 10.95 % ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"and accuracy ( relative recovery ) from 95 % to 115 % .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"The extraction recoveries were greater than 88.42 % for all analytes .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"Dose-dependence was shown for some constituents in the drug concentration-time profiles .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"Among all the active ingredients detected ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"cimifugin had the highest blood concentration ( 881-1510 ng/mL ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"and cycloastragenol had the longest retention time in the rat body ( 15.06-20.44 h ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}, {\"segment_text\": \"Conclusion : This analytical method is a selective ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}, {\"segment_text\": \"sensitive , precise , accurate ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 22}, {\"segment_text\": \"and reliable assay for simultaneous determination of cycloastragenol ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 23}, {\"segment_text\": \"calycosin , formononetin , GMV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 24}, {\"segment_text\": \"and cimifugin in rat plasma .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 25}]}"}]}
{"paper_id": "4a691acb8d49f816a5f377c8ada003ae2d2347c1", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe tertiary structures of the S1 and S2 domains of the spike protein of the coronavirus which is responsible of the severe acute respiratory syndrome ( SARS ) have been recently predicted . Here a molecular assembly of SARS coronavirus peplomer which accounts for the available functional data is suggested . The interaction between S1 and S2 appears to be stabilised by a large hydrophobic network of aromatic side chains present in both domains . This feature results to be common to all coronaviruses , suggesting potential targeting for drugs preventing coronavirus-related infections .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The tertiary structures of the S1 and S2 domains of the spike protein of the coronavirus which is responsible of the severe acute respiratory syndrome ( SARS ) have been recently predicted .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Here a molecular assembly of SARS coronavirus peplomer which accounts for the available functional data is suggested .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"The interaction between S1 and S2 appears to be stabilised by a large hydrophobic network of aromatic side chains present in both domains .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"This feature results to be common to all coronaviruses ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"suggesting potential targeting for drugs preventing coronavirus-related infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}]}"}]}
{"paper_id": "29a014e7f2271e28b2fc9eb2a56028e7a636cf38", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCoxsackie Virus ( H3 ) . Such antiviral properties were mainly explained by virucidal mechanism . Moreover , MLT protected mice which were challenged with lethal doses of pathogenic influenza A H1N1 viruses . Therefore , these results provides the evidence that BV and MLT could be a potential source as a promising antiviral agent , especially to develop as a broad spectrum antiviral agent .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Coxsackie Virus ( H3 ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Such antiviral properties were mainly explained by virucidal mechanism .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Moreover , MLT protected mice which were challenged with lethal doses of pathogenic influenza A H1N1 viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"Therefore , these results provides the evidence that BV and MLT could be a potential source as a promising antiviral agent ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 4}, {\"segment_text\": \"especially to develop as a broad spectrum antiviral agent .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}]}"}]}
{"paper_id": "247d7378386c4c48cf327c151a9ea73040df0403", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nProstate cancer is diagnosed in over 1 million men every year globally , yet current diagnostic modalities are inadequate for identification of significant cancer and more reliable early diagnostic biomarkers are necessary for improved clinical management of prostate cancer patients . MicroRNAs ( miRNAs ) modulate important cellular processes/pathways contributing to cancer and are stably present in body fluids . In this study we profiled 372 cancer-associated miRNAs in plasma collected before ( ~ 60 % patients ) and after/during commencement of treatment ( ~ 40 % patients ) , from age-matched prostate cancer patients and healthy controls , and observed elevated levels of 4 miRNAs - miR-4289 , miR-326 , miR-152-3p and miR-98-5p , which were validated in an independent cohort . The miRNA panel was able to differentiate between prostate cancer patients and controls ( AUC = 0.88 ) . Analysis of published miRNA transcriptomic data from clinical samples demonstrated low expression of miR-152-3p in tumour compared to adjacent non-malignant tissues . Overexpression of miR-152-3p increased proliferation and migration of prostate cancer cells , suggesting a role for this miRNA in prostate cancer pathogenesis , a concept that was supported by pathway analysis of predicted miR-152-3p target genes . In summary , a four miRNA panel , including miR-152-3p which likely targets genes with key roles in prostate cancer pathogenesis , has the potential to improve early prostate cancer diagnosis .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Prostate cancer is diagnosed in over 1 million men every year globally ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"yet current diagnostic modalities are inadequate for identification of significant cancer and more reliable early diagnostic biomarkers are necessary for improved clinical management of prostate cancer patients .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"MicroRNAs ( miRNAs ) modulate important cellular processes/pathways contributing to cancer and are stably present in body fluids .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"In this study we profiled 372 cancer-associated miRNAs in plasma collected before ( ~ 60 % patients ) and after/during commencement of treatment ( ~ 40 % patients ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"from age-matched prostate cancer patients and healthy controls ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"and observed elevated levels of 4 miRNAs - miR-4289 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"miR-326 , miR-152-3p and miR-98-5p ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"which were validated in an independent cohort .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The miRNA panel was able to differentiate between prostate cancer patients and controls ( AUC = 0.88 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Analysis of published miRNA transcriptomic data from clinical samples demonstrated low expression of miR-152-3p in tumour compared to adjacent non-malignant tissues .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"Overexpression of miR-152-3p increased proliferation and migration of prostate cancer cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"suggesting a role for this miRNA in prostate cancer pathogenesis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"a concept that was supported by pathway analysis of predicted miR-152-3p target genes .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"In summary , a four miRNA panel ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"including miR-152-3p which likely targets genes with key roles in prostate cancer pathogenesis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"has the potential to improve early prostate cancer diagnosis .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}]}"}]}
{"paper_id": "583d50e98cc0f57dabf93d306f584ea45f5ae3b0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe etiology and morbidity associated with asthma are thought to stem from both genetic factors and potentially modifiable environmental factors , such as viral infections . ( 1 ) ( 2 ) ( 3 ) ( 4 ) ( 5 ) ( 6 ) ( 7 ) Although it is unclear whether respiratory viral infections cause asthma , observational studies have demonstrated a high rate of asthma in children with a history of severe viral lower respiratory tract infections during infancy , and viruses are the associated with the majority of asthma exacerbations among both children and adults . This review will discuss the pathogens associated with virus-induced wheezing illnesses during infancy and early childhood , the association of bronchiolitis during infancy with an increased risk of childhood asthma , and the association of respiratory viruses with asthma exacerbations in older children and adults .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The etiology and morbidity associated with asthma are thought to stem from both genetic factors and potentially modifiable environmental factors , such as viral infections .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"( 1 ) ( 2 ) ( 3 ) ( 4 ) ( 5 ) ( 6 ) ( 7 ) Although it is unclear whether respiratory viral infections cause asthma ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"observational studies have demonstrated a high rate of asthma in children with a history of severe viral lower respiratory tract infections during infancy ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"and viruses are the associated with the majority of asthma exacerbations among both children and adults .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"This review will discuss the pathogens associated with virus-induced wheezing illnesses during infancy and early childhood ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"the association of bronchiolitis during infancy with an increased risk of childhood asthma ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"and the association of respiratory viruses with asthma exacerbations in older children and adults .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}]}"}]}
{"paper_id": "8286205b20cbc046d9fdc8a19368f9d043b0d88b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nInterest in the potential of monoclonal antibodies ( mAbs ) to serve as therapeutic agents has surged in the past decade with a major emphasis on human viral diseases . There has been much attention in this area directed towards the human immunodeficiency virus type-1 ( HIV-1 ) and promising research developments have emerged on the inhibition of HIV-1 infection by mAbs and the identification of several highly conserved neutralizing epitopes . More recently , potent fully-human neutralizing mAbs have been developed against a variety of important human viral disease agents including the paramyxoviruses Hendra virus and Nipah virus , and human or humanized mAbs have been developed against severe acute respiratory syndrome coronavirus ( SARS CoV ) , and West Nile virus , among others . Most of these more recently developed antiviral mAbs have come from the use of antibody phage-display technologies and the implementation of simplified , inexpensive yet efficient methods , for expressing and purifying the initially selected fragment antibodies is of prime importance in further facilitating this area of research .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Interest in the potential of monoclonal antibodies ( mAbs ) to serve as therapeutic agents has surged in the past decade with a major emphasis on human viral diseases .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"There has been much attention in this area directed towards the human immunodeficiency virus type-1 ( HIV-1 ) and promising research developments have emerged on the inhibition of HIV-1 infection by mAbs and the identification of several highly conserved neutralizing epitopes .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"More recently , potent fully-human neutralizing mAbs have been developed against a variety of important human viral disease agents including the paramyxoviruses Hendra virus and Nipah virus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"and human or humanized mAbs have been developed against severe acute respiratory syndrome coronavirus ( SARS CoV ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"and West Nile virus , among others .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Most of these more recently developed antiviral mAbs have come from the use of antibody phage-display technologies and the implementation of simplified ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"inexpensive yet efficient methods , for expressing and purifying the initially selected fragment antibodies is of prime importance in further facilitating this area of research .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}]}"}]}
{"paper_id": "2abe82dfebe721e4d1809bdc9a9d0f38019d1be3", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAs the global COVID-19 pandemic escalates there is a need within radiation oncology to work to support our patients in the best way possible . Measures are required to reduce infection spread between patients and within the workforce . Departments need contingency planning to create capacity and continue essential treatments despite a reduced workforce . The #radonc community held an urgent online journal club on Twitter in March 2020 to discuss these issues and create some consensus on crucial next steps . There were 121 global contributors . This document summarises these discussions around themes of infection prevention , rationalisation of workload and working practice in the presence of infection .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"As the global COVID-19 pandemic escalates there is a need within radiation oncology to work to support our patients in the best way possible .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Measures are required to reduce infection spread between patients and within the workforce .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Departments need contingency planning to create capacity and continue essential treatments despite a reduced workforce .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"The #radonc community held an urgent online journal club on Twitter in March 2020 to discuss these issues and create some consensus on crucial next steps .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"There were 121 global contributors .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"This document summarises these discussions around themes of infection prevention ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"rationalisation of workload and working practice in the presence of infection .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}]}"}]}
{"paper_id": "e226beab8af4202a5182f7603fe468dedd5dee6a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nInspired by bioactive biaryl-containing natural products found in plants and the marine 19 environment , a series of synthetic compounds belonging to the azaBINOL chiral ligand family 20 was evaluated for antiviral activity against HIV-1 . Testing of 39 unique azaBINOLs in a single-21 round infectivity assay resulted in the identification of three promising antiviral compounds , 22 including 7-isopropoxy-8 - ( naphth-1-yl ) quinoline ( azaBINOL B # 24 ) , which exhibited low-23 micromolar activity . The active compounds and several close structural analogues were further 24 tested against three different HIV-1 envelope pseudotyped viruses as well as in a full-virus 25 replication system ( EASY-HIT ) . Mode-of-action studies using a time-of-addition assay indicated 26 that azaBINOL B # 24 acts after viral entry but before viral assembly and budding . HIV-1 reverse 27 transcriptase ( RT ) assays that individually test for polymerase and RNase H activity were used to 28 demonstrate that B # 24 inhibits RNase H activity , most likely allosterically . Further binding 29 analysis using bio-layer interferometry ( BLI ) showed that B # 24 interacts with HIV-1 RT in a 30 highly specific manner . These results indicate that azaBINOL B # 24 is a potentially viable , novel 31\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Inspired by bioactive biaryl-containing natural products found in plants and the marine 19 environment ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"a series of synthetic compounds belonging to the azaBINOL chiral ligand family 20 was evaluated for antiviral activity against HIV-1 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Testing of 39 unique azaBINOLs in a single-21 round infectivity assay resulted in the identification of three promising antiviral compounds , 22\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"including 7-isopropoxy-8 - ( naphth-1-yl ) quinoline ( azaBINOL B # 24 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"which exhibited low-23 micromolar activity .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"The active compounds and several close structural analogues were further 24 tested against three different HIV-1 envelope pseudotyped viruses as well as in a full-virus 25\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"replication system ( EASY-HIT ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Mode-of-action studies using a time-of-addition assay indicated 26 that azaBINOL B # 24 acts after viral entry but before viral assembly and budding .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"HIV-1 reverse 27 transcriptase ( RT ) assays that individually test for polymerase and RNase H activity were used to 28 demonstrate that B # 24 inhibits RNase H activity , most likely allosterically .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Further binding 29 analysis using bio-layer interferometry ( BLI ) showed that B # 24 interacts with HIV-1 RT in a 30 highly specific manner .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"These results indicate that azaBINOL B # 24 is a potentially viable , novel 31\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}]}"}]}
{"paper_id": "ba7fc2e5541679edbb6be160fe327838f9762100", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nFaecal samples were taken from cats living in multi-cat households with endemic feline coronavirus ( FCoV ) infection . Total RNA was extracted from faecal suspensions and FCoV RNA was quantified using a real-time reverse transcriptase-polymerase chain reaction ( RT-PCR ) assay . The real-time RT-PCR threshold cycle ( C T ) values were consistently high suggesting that the samples contained very little viral RNA . However , experiments in which RNA extracted from FCoV-infected cell culture supernatants was combined with RNA extracted from faecal suspensions revealed the presence of faecal factors that significantly inhibited the reverse transcription reaction . Consequently , three methods of RNA extraction were investigated and RNA dilution was undertaken to investigate whether the effects of the faecal inhibitors could be reduced . Our results show that using the QIAgen RNA mini kit for RNA extraction and dilution of the RNA samples helps to reduce the inhibitory effects . However , because the extent of the inhibitory effects varied between faecal samples , accurate quantification proved difficult . We , therefore , conclude that although real-time RT-PCR provides an excellent method for detecting the presence of viral shedding , quantification of FCoV RNA in faecal material has to take into account the possible effects of RT-PCR inhibitors . It is , therefore , essential that all new assays , and the methods of sample preparation , are carefully evaluated before being used in a clinical setting .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Faecal samples were taken from cats living in multi-cat households with endemic feline coronavirus ( FCoV ) infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Total RNA was extracted from faecal suspensions and FCoV RNA was quantified using a real-time reverse transcriptase-polymerase chain reaction ( RT-PCR ) assay .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"The real-time RT-PCR threshold cycle ( C T ) values were consistently high suggesting that the samples contained very little viral RNA .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"However , experiments in which RNA extracted from FCoV-infected cell culture supernatants was combined with RNA extracted from faecal suspensions revealed the presence of faecal factors that significantly inhibited the reverse transcription reaction .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Consequently , three methods of RNA extraction were investigated and RNA dilution was undertaken to investigate whether the effects of the faecal inhibitors could be reduced .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Our results show that using the QIAgen RNA mini kit for RNA extraction and dilution of the RNA samples helps to reduce the inhibitory effects .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"However , because the extent of the inhibitory effects varied between faecal samples , accurate quantification proved difficult .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"We , therefore , conclude that although real-time RT-PCR provides an excellent method for detecting the presence of viral shedding ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"quantification of FCoV RNA in faecal material has to take into account the possible effects of RT-PCR inhibitors .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"It is , therefore , essential that all new assays ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"and the methods of sample preparation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"are carefully evaluated before being used in a clinical setting .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}]}"}]}
{"paper_id": "c05522c7132d3162d433c02ade1fc80604625a4f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAlthough less is known about the ability of antibodies to mediate demyelination , the presence of oligoclonally expanded B cells and high concentrations of antibodies ( against self or infectious agents ) in the central nervous system of many multiple sclerosis patients suggests that antibodies may also contribute to myelin destruction . Here , we show that anti-JHM antibodies , in the absence of T or B cells , caused demyelination in JHM-infected mice . Anti-JHM antibody was detected adjacent to areas of demyelination , consistent with a direct interaction between antibody and infected cells . Demyelination was reduced by 85 to 90 % in infected RAG1 ؊ / ؊ mice lacking normal expression of activating Fc receptors ( FcR ␥ ؊ / ؊ ) and by ϳ76 % when complement was depleted by treatment with cobra venom factor . These data demonstrate that JHM-specific antibodies are sufficient to cause demyelination and that myelin destruction in the presence of anti-virus antibodies results from a combination of complement-and Fc receptor-dependent mechanisms . ( Am J Pathol 2005 , 166:801-809 )\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Although less is known about the ability of antibodies to mediate demyelination ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"the presence of oligoclonally expanded B cells and high concentrations of antibodies ( against self or infectious agents ) in the central nervous system of many multiple sclerosis patients suggests that antibodies may also contribute to myelin destruction .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Here , we show that anti-JHM antibodies ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"in the absence of T or B cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"caused demyelination in JHM-infected mice .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Anti-JHM antibody was detected adjacent to areas of demyelination ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"consistent with a direct interaction between antibody and infected cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Demyelination was reduced by 85 to 90 % in infected RAG1 ؊ / ؊ mice lacking normal expression of activating Fc receptors ( FcR ␥ ؊ / ؊ ) and by ϳ76 % when complement was depleted by treatment with cobra venom factor .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"These data demonstrate that JHM-specific antibodies are sufficient to cause demyelination and that myelin destruction in the presence of anti-virus antibodies results from a combination of complement-and Fc receptor-dependent mechanisms .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"( Am J Pathol 2005 , 166:801-809 )\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 10}]}"}]}
{"paper_id": "eb715af6ecf15c3fccecb3012cd391569d292f76", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAdvances in free radical research show that reactive oxygen and nitrogen oxide species , for example superoxide , nitric oxide ( NO ) and peroxynitrite , play an important role in the pathogenesis of different viral infections , including dengue virus . The pathogenic mechanism of dengue haemorrhagic fever ( DHF ) is complicated and is not clearly understood . The hallmarks of the dengue disease , the antibody-dependent enhancement , the shift from T-helper type 1 ( Th1 ) to Th2 cytokine response and the cytokine tsunami resulting in vascular leakage can now be explained much better with the knowledge gained about NO and peroxynitrite . This paper makes an effort to present a synthesis of the current opinions to explain the pathogenesis of DHF/shock syndrome with NO on centre stage .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Advances in free radical research show that reactive oxygen and nitrogen oxide species ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"for example superoxide , nitric oxide ( NO ) and peroxynitrite ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"play an important role in the pathogenesis of different viral infections , including dengue virus .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The pathogenic mechanism of dengue haemorrhagic fever ( DHF ) is complicated and is not clearly understood .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"The hallmarks of the dengue disease ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"the antibody-dependent enhancement , the shift from T-helper type 1 ( Th1 ) to Th2 cytokine response and the cytokine tsunami resulting in vascular leakage can now be explained much better with the knowledge gained about NO and peroxynitrite .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"This paper makes an effort to present a synthesis of the current opinions to explain the pathogenesis of DHF/shock syndrome with NO on centre stage .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}]}"}]}
{"paper_id": "07fc7bb8cbdb82bd4b17681aa92a6fc06d5fcf82", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe coronavirus replicase-transcriptase complex is an assembly of viral and cellular proteins that mediate the synthesis of genome and subgenome-sized mRNAs in the virus-infected cell . Here , we report a genetic and functional analysis of 19 temperature-sensitive ( ts ) mutants of Murine hepatitis virus MHV-A59 that are unable to synthesize viral RNA when the infection is initiated and maintained at the non-permissive temperature . Both classical and biochemical complementation analysis leads us to predict that the majority of MHV-A59 ORF1a replicase gene products ( nonstructural proteins nsp1-nsp11 ) form a single complementation group ( cistron1 ) while the replicase gene products encoded in ORF1b ( non-structural proteins nsp12-nsp16 ) are able to function in trans and comprise at least three , and possibly five , further complementation groups ( cistrons II-VI ) . Also , we have identified mutations in the non-structural proteins nsp 4 , nsp5 , nsp10 , nsp12 , nsp14 , and nsp16 that are responsible for the ts phenotype of eight MHV-A59 mutants , which allows us to conclude that these proteins are essential for the assembly of a functional replicasetranscriptase complex . Finally , our analysis of viral RNA synthesis in ts mutant virus-infected cells allows us to discriminate three phenotypes with regard to the inability of specific mutants to synthesize viral RNA at the nonpermissive temperature . Mutant LA ts6 appeared to be defective in continuing negative-strand synthesis , mutant Alb ts16 appeared to form negative strands but these were not utilized for positive-strand RNA synthesis , and mutant Alb ts22 was defective in the elongation of both positive-and negative-strand RNA . On the basis of these results , we propose a model that describes a pathway for viral RNA synthesis in MHV-A59-infected cells . Further biochemical analysis of these mutants should allow us to identify intermediates in this pathway and elucidate the precise function ( s ) of the viral replicase proteins involved . Citation : Sawicki SG , Sawicki DL , Younker D , Meyer Y , Thiel V , et al. ( 2005 ) Functional and genetic analysis of coronavirus replicase-transcriptase proteins . PLoS Pathog 1 ( 4 ) : e39 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The coronavirus replicase-transcriptase complex is an assembly of viral and cellular proteins that mediate the synthesis of genome and subgenome-sized mRNAs in the virus-infected cell .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Here , we report a genetic and functional analysis of 19 temperature-sensitive ( ts ) mutants of Murine hepatitis virus MHV-A59 that are unable to synthesize viral RNA when the infection is initiated and maintained at the non-permissive temperature .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Both classical and biochemical complementation analysis leads us to predict that the majority of MHV-A59 ORF1a replicase gene products ( nonstructural proteins nsp1-nsp11 ) form a single complementation group ( cistron1 ) while the replicase gene products encoded in ORF1b ( non-structural proteins nsp12-nsp16 ) are able to function in trans and comprise at least three ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"and possibly five , further complementation groups ( cistrons II-VI ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Also , we have identified mutations in the non-structural proteins nsp 4 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"nsp5 , nsp10 , nsp12 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"nsp14 , and nsp16 that are responsible for the ts phenotype of eight MHV-A59 mutants ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"which allows us to conclude that these proteins are essential for the assembly of a functional replicasetranscriptase complex .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Finally , our analysis of viral RNA synthesis in ts mutant virus-infected cells allows us to discriminate three phenotypes with regard to the inability of specific mutants to synthesize viral RNA at the nonpermissive temperature .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Mutant LA ts6 appeared to be defective in continuing negative-strand synthesis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"mutant Alb ts16 appeared to form negative strands but these were not utilized for positive-strand RNA synthesis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"and mutant Alb ts22 was defective in the elongation of both positive-and negative-strand RNA .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"On the basis of these results ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"we propose a model that describes a pathway for viral RNA synthesis in MHV-A59-infected cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Further biochemical analysis of these mutants should allow us to identify intermediates in this pathway and elucidate the precise function ( s ) of the viral replicase proteins involved .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"Citation : Sawicki SG , Sawicki DL ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 16}, {\"segment_text\": \"Younker D , Meyer Y ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 17}, {\"segment_text\": \"Thiel V , et al. ( 2005 ) Functional and genetic analysis of coronavirus replicase-transcriptase proteins .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 18}, {\"segment_text\": \"PLoS Pathog 1 ( 4 ) : e39 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 19}]}"}]}
{"paper_id": "d9a9553aa9b46fb7e1db899a5fddd08ad00a632a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nKorea has adopted Epidemic Intelligence Service ( EIS ) officers through the Field Epidemiology Training Program ( FETP ) since 1999 for systematic control of emerging and re-emerging infectious diseases . Graduates of medical schools in Korea are selected and serve as public health doctors ( PHDs ) for their mandatory military service . The duration of service is 3 years and PHDs comprise general practitioners and specialists . Some PHDs are selected as EIS officers with 3 weeks basic FETP training and work for central and provincial public health authorities to conduct epidemiological investigations . The total number of EIS officers is 31 as of 2012 . The Korea Centers for Disease Control and Prevention ( KCDC ) has 12 specialists , whereas specialists and each province has one or two EIS officers to administer local epidemiological investigations in 253 public health centers . The Korean EIS officers have successfully responded and prevented infectious diseases , but there is a unique limitation : the number of PHDs in Korea is decreasing and PHDs are not allowed to stay outside Korea , which makes it difficult to cope with overseas infectious diseases . Furthermore , after 3 years service , they quit and their experiences are not accumulated . KCDC has hired full-time EIS officers since 2012 to overcome this limitation .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Korea has adopted Epidemic Intelligence Service ( EIS ) officers through the Field Epidemiology Training Program ( FETP ) since 1999 for systematic control of emerging and re-emerging infectious diseases .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Graduates of medical schools in Korea are selected and serve as public health doctors ( PHDs ) for their mandatory military service .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"The duration of service is 3 years and PHDs comprise general practitioners and specialists .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Some PHDs are selected as EIS officers with 3 weeks basic FETP training and work for central and provincial public health authorities to conduct epidemiological investigations .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"The total number of EIS officers is 31 as of 2012 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"The Korea Centers for Disease Control and Prevention ( KCDC ) has 12 specialists ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"whereas specialists and each province has one or two EIS officers to administer local epidemiological investigations in 253 public health centers .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"The Korean EIS officers have successfully responded and prevented infectious diseases ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"but there is a unique limitation : the number of PHDs in Korea is decreasing and PHDs are not allowed to stay outside Korea ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"which makes it difficult to cope with overseas infectious diseases .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Furthermore , after 3 years service ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"they quit and their experiences are not accumulated .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"KCDC has hired full-time EIS officers since 2012 to overcome this limitation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "7b7cf3bd29c1cfbac643c487c643b07a827e3aa2", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAim : The aim of the study was to examine , among hospital employees exposed to an outbreak of severe acute respiratory syndrome ( SARS ) , post-outbreak levels of depressive symptoms and the relationship between those depressive symptom levels and the types of outbreak event exposures experienced . Methods : In 2006 , randomly selected employees ( N = 549 ) of a hospital in Beijing were surveyed concerning their exposures to the city 's 2003 SARS outbreak and the ways in which the outbreak had affected their mental health . Subjects were assessed on sociodemographic factors , on types of exposure to the outbreak , and on symptoms of posttraumatic stress disorder and depression . Results : The results of multinomial regression analyses showed that , with other relevant factors controlled for , being single , having been quarantined during the outbreak , having been exposed to other traumatic events before SARS , and perceived SARS-related risk level during the outbreak were found to increase the odds of having a high level of depressive symptoms 3 years later . Altruistic acceptance of risk during the outbreak was found to decrease the odds of high post-outbreak depressive symptom levels . Conclusions : Policy makers and mental health professionals working to prepare for potential disease outbreaks should be aware that the experience of being quarantined can , in some cases , lead to long-term adverse mental health consequences .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Aim : The aim of the study was to examine ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"among hospital employees exposed to an outbreak of severe acute respiratory syndrome ( SARS ) ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"post-outbreak levels of depressive symptoms and the relationship between those depressive symptom levels and the types of outbreak event exposures experienced .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"Methods : In 2006 , randomly selected employees ( N = 549 ) of a hospital in Beijing were surveyed concerning their exposures to the city 's 2003 SARS outbreak and the ways in which the outbreak had affected their mental health .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Subjects were assessed on sociodemographic factors ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"on types of exposure to the outbreak ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"and on symptoms of posttraumatic stress disorder and depression .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Results : The results of multinomial regression analyses showed that ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"with other relevant factors controlled for ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"being single , having been quarantined during the outbreak ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"having been exposed to other traumatic events before SARS ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and perceived SARS-related risk level during the outbreak were found to increase the odds of having a high level of depressive symptoms 3 years later .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Altruistic acceptance of risk during the outbreak was found to decrease the odds of high post-outbreak depressive symptom levels .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Conclusions : Policy makers and mental health professionals working to prepare for potential disease outbreaks should be aware that the experience of being quarantined can ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"in some cases , lead to long-term adverse mental health consequences .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}]}"}]}
{"paper_id": "45d421f19615b936de0527809bb71e12be89fa7c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nTo rapidly distinguish Canine distemper virus ( CDV ) , canine parvovirus ( CPV ) , and canine kobuvirus ( CaKoV ) in practice , a one-step multiplex PCR/RT-PCR assay was developed , with detection limits of 10 2.1 TCID 50 for CDV , 10 1.9 TCID 50 for CPV and 10 3 copies for CaKoV . This method did not amplify nonspecific DNA or RNA from other canine viruses . Therefore , the assay provides a sensitive tool for the rapid clinical detection and epidemiological surveillance of CDV , CPV and CaKoV in dogs .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"To rapidly distinguish Canine distemper virus ( CDV ) ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"canine parvovirus ( CPV ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"and canine kobuvirus ( CaKoV ) in practice ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"a one-step multiplex PCR/RT-PCR assay was developed ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"with detection limits of 10 2.1 TCID 50 for CDV ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"10 1.9 TCID 50 for CPV and 10 3 copies for CaKoV .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"This method did not amplify nonspecific DNA or RNA from other canine viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Therefore , the assay provides a sensitive tool for the rapid clinical detection and epidemiological surveillance of CDV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"CPV and CaKoV in dogs .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}]}"}]}
{"paper_id": "335b0a3f21f764adcbe20ff71e422d823c410098", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Gray wolves ( Canis lupus ) were reintroduced into Yellowstone National Park ( YNP ) after a .70 year absence , and as part of recovery efforts , the population has been closely monitored . In 1999 and 2005 , pup survival was significantly reduced , suggestive of disease outbreaks . Methodology/Principal Findings : We analyzed sympatric wolf , coyote ( Canis latrans ) , and red fox ( Vulpes vulpes ) serologic data from YNP , spanning 1991-2007 , to identify long-term patterns of pathogen exposure , identify associated risk factors , and examine evidence for disease-induced mortality among wolves for which there were survival data . We found high , constant exposure to canine parvovirus ( wolf seroprevalence : 100 % ; coyote : 94 % ) , canine adenovirus-1 ( wolf pups ( 0.5-0.9 yr ) : 91 % , adults ( $ 1 yr ) : 96 % ; coyote juveniles ( 0.5-1.5 yrs ) : 18 % , adults ( $ 1.6 yrs ) : 83 % ) , and canine herpesvirus ( wolf : 87 % ; coyote juveniles : 23 % , young adults ( 1.6-4.9 yrs ) : 51 % , old adults ( $ 5 yrs ) : 87 % ) suggesting that these pathogens were enzootic within YNP wolves and coyotes . An average of 50 % of wolves exhibited exposure to the protozoan parasite , Neospora caninum , although individuals ' odds of exposure tended to increase with age and was temporally variable . Wolf , coyote , and fox exposure to canine distemper virus ( CDV ) was temporally variable , with evidence for distinct multi-host outbreaks in 1999 and 2005 , and perhaps a smaller , isolated outbreak among wolves in the interior of YNP in 2002 . The years of high wolf-pup mortality in 1999 and 2005 in the northern region of the park were correlated with peaks in CDV seroprevalence , suggesting that CDV contributed to the observed mortality . Conclusions/Significance : Of the pathogens we examined , none appear to jeopardize the long-term population of canids in YNP . However , CDV appears capable of causing short-term population declines . Additional information on how and where CDV is maintained and the frequency with which future epizootics might be expected might be useful for future management of the Northern Rocky Mountain wolf population .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Gray wolves ( Canis lupus ) were reintroduced into Yellowstone National Park ( YNP ) after a .70 year absence ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"and as part of recovery efforts ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"the population has been closely monitored .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"In 1999 and 2005 , pup survival was significantly reduced , suggestive of disease outbreaks .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Methodology/Principal Findings : We analyzed sympatric wolf ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"coyote ( Canis latrans ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"and red fox ( Vulpes vulpes ) serologic data from YNP ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"spanning 1991-2007 , to identify long-term patterns of pathogen exposure ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"identify associated risk factors , and examine evidence for disease-induced mortality among wolves for which there were survival data .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"We found high , constant exposure to canine parvovirus ( wolf seroprevalence : 100 % ; coyote : 94 % ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"canine adenovirus-1 ( wolf pups ( 0.5-0.9 yr ) : 91 % ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"adults ( $ 1 yr ) : 96 % ; coyote juveniles ( 0.5-1.5 yrs ) : 18 % ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"adults ( $ 1.6 yrs ) : 83 % ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"and canine herpesvirus ( wolf : 87 % ; coyote juveniles : 23 % , young adults ( 1.6-4.9 yrs ) : 51 % ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"old adults ( $ 5 yrs ) : 87 % ) suggesting that these pathogens were enzootic within YNP wolves and coyotes .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"An average of 50 % of wolves exhibited exposure to the protozoan parasite ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Neospora caninum , although individuals ' odds of exposure tended to increase with age and was temporally variable .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Wolf , coyote , and fox exposure to canine distemper virus ( CDV ) was temporally variable ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"with evidence for distinct multi-host outbreaks in 1999 and 2005 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"and perhaps a smaller , isolated outbreak among wolves in the interior of YNP in 2002 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"The years of high wolf-pup mortality in 1999 and 2005 in the northern region of the park were correlated with peaks in CDV seroprevalence ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"suggesting that CDV contributed to the observed mortality .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"Conclusions/Significance : Of the pathogens we examined ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"none appear to jeopardize the long-term population of canids in YNP .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}, {\"segment_text\": \"However , CDV appears capable of causing short-term population declines .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 25}, {\"segment_text\": \"Additional information on how and where CDV is maintained and the frequency with which future epizootics might be expected might be useful for future management of the Northern Rocky Mountain wolf population .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 26}]}"}]}
{"paper_id": "c146ea9fadc16cfc9571f748391f3aa07f5acbd7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nHouttuynia cordata is an important traditional Chinese herb with unresolved genetics and taxonomy , which lead to potential problems in the conservation and utilization of the resource . Inter-simple sequence repeat ( ISSR ) markers were used to assess the level and distribution of genetic diversity in 226 individuals from 15 populations of H. cordata in China . ISSR analysis revealed low genetic variations within populations but high genetic differentiations among populations . This genetic structure probably mainly reflects the historical association among populations . Genetic cluster analysis showed that the basal clade is composed of populations from Southwest China , and the other populations have continuous and eastward distributions . The structure of genetic diversity in H. cordata demonstrated that this species might have survived in Southwest China during the glacial age , and subsequently experienced an eastern postglacial expansion . Based on the results of genetic analysis , it was proposed that as many as possible targeted populations for conservation be included .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Houttuynia cordata is an important traditional Chinese herb with unresolved genetics and taxonomy ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"which lead to potential problems in the conservation and utilization of the resource .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Inter-simple sequence repeat ( ISSR ) markers were used to assess the level and distribution of genetic diversity in 226 individuals from 15 populations of H. cordata in China .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"ISSR analysis revealed low genetic variations within populations but high genetic differentiations among populations .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"This genetic structure probably mainly reflects the historical association among populations .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"Genetic cluster analysis showed that the basal clade is composed of populations from Southwest China ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"and the other populations have continuous and eastward distributions .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"The structure of genetic diversity in H. cordata demonstrated that this species might have survived in Southwest China during the glacial age ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"and subsequently experienced an eastern postglacial expansion .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Based on the results of genetic analysis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"it was proposed that as many as possible targeted populations for conservation be included .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}]}"}]}
{"paper_id": "cb265a65f94e7f825fb2d324cdd89dcbda385e5c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCoronavirus E protein is a small viral envelope protein that plays an essential role in coronavirus assembly ; coexpression of coronavirus M and E proteins results in the production of virus-like particles . The present study demonstrated that mouse hepatitis virus ( MHV ) E protein was released as an integral membrane protein in lipid vesicles from E-protein-expressing mammalian cells , in the absence of other MHV proteins . Furthermore , our data indicated that the E-protein-containing vesicles , which had a slightly lighter buoyant density than that of MHV , were released from MHV-infected cells . These data implied that E protein alone can drive the production and release of coronavirus envelope in the absence of M protein .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Coronavirus E protein is a small viral envelope protein that plays an essential role in coronavirus assembly ; coexpression of coronavirus M and E proteins results in the production of virus-like particles .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The present study demonstrated that mouse hepatitis virus ( MHV ) E protein was released as an integral membrane protein in lipid vesicles from E-protein-expressing mammalian cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"in the absence of other MHV proteins .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"Furthermore , our data indicated that the E-protein-containing vesicles ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 4}, {\"segment_text\": \"which had a slightly lighter buoyant density than that of MHV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"were released from MHV-infected cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"These data implied that E protein alone can drive the production and release of coronavirus envelope in the absence of M protein .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}]}"}]}
{"paper_id": "d30d65c79f829da5b5b281b91559ea6b8d8228a8", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBoth full-length and subgenomic negative-strand RNAs are initiated at the 3 terminus of the positive-strand genomic RNA of the arterivirus , simian hemorrhagic fever virus ( SHFV ) . The SHFV 3 ( + ) non-coding region ( NCR ) is 76 nts in length and forms a stem loop ( SL ) structure that was confirmed by ribonuclease structure probing . Two cell proteins , p56 and p42 , bound specifically to a probe consisting of the SHFV 3 ( + ) NCR RNA . The 3 ( + ) NCR RNAs of two additional members of the arterivirus genus specifically interacted with two cell proteins of the same size . p56 was identified as polypyrimidine tract-binding protein ( PTB ) and p42 was identified as fructose bisphosphate aldolase A. PTB binding sites were mapped to a terminal loop and to a bulged region of the SHFV 3 SL structure . Deletion of either of the PTB binding sites in the viral RNA significantly reduced PTB binding activity , suggesting that both sites are required for efficient binding of this protein . Changes in the top portion of the SHFV 3 SL structure eliminated aldolase binding , suggesting that the binding site for this protein is located near the top of the SL . These cell proteins may play roles in regulating the functions of the genomic 3 NCR .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Both full-length and subgenomic negative-strand RNAs are initiated at the 3 terminus of the positive-strand genomic RNA of the arterivirus ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"simian hemorrhagic fever virus ( SHFV ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"The SHFV 3 ( + ) non-coding region ( NCR ) is 76 nts in length and forms a stem loop ( SL ) structure that was confirmed by ribonuclease structure probing .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Two cell proteins , p56 and p42 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"bound specifically to a probe consisting of the SHFV 3 ( + ) NCR RNA .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"The 3 ( + ) NCR RNAs of two additional members of the arterivirus genus specifically interacted with two cell proteins of the same size .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"p56 was identified as polypyrimidine tract-binding protein ( PTB ) and p42 was identified as fructose bisphosphate aldolase A. PTB binding sites were mapped to a terminal loop and to a bulged region of the SHFV 3 SL structure .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Deletion of either of the PTB binding sites in the viral RNA significantly reduced PTB binding activity ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"suggesting that both sites are required for efficient binding of this protein .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Changes in the top portion of the SHFV 3 SL structure eliminated aldolase binding ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"suggesting that the binding site for this protein is located near the top of the SL .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"These cell proteins may play roles in regulating the functions of the genomic 3 NCR .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "ab51b7f0f30737bd7beb5c19baa5774ade9bccda", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAdults who did not work in the outbreak were worse in mental and physical health , distress and life satisfaction . The identification of whose health and wellbeing is more affected by the disruption enables more targeted assistance . The early evidence from China can help countries that consider implementing confinement policies to contain COVID-19 . We assess the health and wellbeing of normal adults living and working after one month of confinement to contain the COVID-19 outbreak in China . On Feb 20-21 , 2020 , we surveyed 369 adults in 64 cities in China that varied in their rates of confirmed coronavirus cases on their health conditions , distress and life satisfaction . 27 % of the participants worked at the office , 38 % resorted to working from home , and 25 % stopped working due to the outbreak . Those who stopped working reported worse mental and physical health conditions as well as distress . The severity of in an individual 's home city predicts their life satisfaction , and this relationship is contingent upon individuals ' existing chronic health issues and their hours of exercise . Our evidence supports the need to pay attention to the health of people who were not affected by the virus epidemiologically , especially for people who stopped working during the outbreak . Our results highlight that physically active people might be more susceptible to wellbeing issues during the lockdown . Policymakers who are considering introducing restrictive measures to contain COVID-19 may benefit from understanding such health and wellbeing implications .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Adults who did not work in the outbreak were worse in mental and physical health , distress and life satisfaction .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"The identification of whose health and wellbeing is more affected by the disruption enables more targeted assistance .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"The early evidence from China can help countries that consider implementing confinement policies to contain COVID-19 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"We assess the health and wellbeing of normal adults living and working after one month of confinement to contain the COVID-19 outbreak in China .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"On Feb 20-21 , 2020 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"we surveyed 369 adults in 64 cities in China that varied in their rates of confirmed coronavirus cases on their health conditions , distress and life satisfaction .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"27 % of the participants worked at the office ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"38 % resorted to working from home ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and 25 % stopped working due to the outbreak .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Those who stopped working reported worse mental and physical health conditions as well as distress .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The severity of in an individual 's home city predicts their life satisfaction ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and this relationship is contingent upon individuals ' existing chronic health issues and their hours of exercise .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Our evidence supports the need to pay attention to the health of people who were not affected by the virus epidemiologically ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"especially for people who stopped working during the outbreak .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Our results highlight that physically active people might be more susceptible to wellbeing issues during the lockdown .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Policymakers who are considering introducing restrictive measures to contain COVID-19 may benefit from understanding such health and wellbeing implications .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "7a3b1df462ac5224e195a12287ee156064910bf0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nTo cite : Rabinowitz PMacG , Pappaioanou M , Bardosh KL , et al. . A planetary vision for one health .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"To cite : Rabinowitz PMacG ,\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 1}, {\"segment_text\": \"Pappaioanou M , Bardosh KL , et al. .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 2}, {\"segment_text\": \"A planetary vision for one health .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 3}]}"}]}
{"paper_id": "d7cb7c135b8d3727e626d35b7b1ec92f2400e78b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThis overview describes the main categories of specific occupational disorders and it covers also how work exposures are potential determinants of common respiratory conditions . Acute inhalation injuries may present as inhalation fever or as acute tracheobronchitis and pneumonitis . Occupational asthma is the most frequent work-related respiratory disease . It may be caused by allergic sensitization to macromolecules of biologic origin or to chemicals of low molecular weight , as well as by ( heavy ) exposure to workplace irritants . The pneumoconioses are caused by the accumulation of dust particles or fibres in the lungs . They include silicosis , coal workers ' pneumoconioses , asbestosis and other less common pneumoconioses . Chronic beryllium disease is caused by a cell-mediated sensitization to beryllium and resembles sarcoidosis . Hard-metal lung disease is caused by sensitivity to cobalt and resembles hypersensitivity pneumonitis . Extrinsic allergic alveolitis or hypersensitivity pneumonitis is generally caused by sensitization to aerosolized biological antigens . Several types of infections may be related more or less specifically to work . Chronic obstructive lung disease is mainly caused by cigarette smoking , but exposure to dusts and gases contribute to its incidence . Similarly , bronchopulmonary cancer is not only caused by smoking , but also by occupational agents , most notably asbestos . Asbestos is also a cause of nonmalignant and malignant pleural disease .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"This overview describes the main categories of specific occupational disorders and it covers also how work exposures are potential determinants of common respiratory conditions .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Acute inhalation injuries may present as inhalation fever or as acute tracheobronchitis and pneumonitis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Occupational asthma is the most frequent work-related respiratory disease .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"It may be caused by allergic sensitization to macromolecules of biologic origin or to chemicals of low molecular weight ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"as well as by ( heavy ) exposure to workplace irritants .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"The pneumoconioses are caused by the accumulation of dust particles or fibres in the lungs .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"They include silicosis , coal workers ' pneumoconioses ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"asbestosis and other less common pneumoconioses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"Chronic beryllium disease is caused by a cell-mediated sensitization to beryllium and resembles sarcoidosis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Hard-metal lung disease is caused by sensitivity to cobalt and resembles hypersensitivity pneumonitis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Extrinsic allergic alveolitis or hypersensitivity pneumonitis is generally caused by sensitization to aerosolized biological antigens .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Several types of infections may be related more or less specifically to work .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Chronic obstructive lung disease is mainly caused by cigarette smoking ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"but exposure to dusts and gases contribute to its incidence .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Similarly , bronchopulmonary cancer is not only caused by smoking ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"but also by occupational agents , most notably asbestos .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Asbestos is also a cause of nonmalignant and malignant pleural disease .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "b3e94bce63878a41d45d22c012a9492d079b3b7f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nChronic hepatitis B virus ( HBV ) infection , affecting approximately 240 million people worldwide , is a major public health problem that elevates the risk of developing liver cirrhosis and hepatocellular carcinoma . Given that current anti-HBV drugs are limited to interferon-based regimens and nucleos ( t ) ide analogs , the development of new anti-HBV agents is urgently needed . The viral entry process is generally an attractive target implicated in antiviral strategies . Using primary cells from humans and Tupaia belangeri , as well as HepaRG cells , important determinants of viral entry have been achieved . Recently , sodium taurocholate cotransporting polypeptide ( NTCP ) was identified as an HBV entry receptor and enabled the establishment of a susceptible cell line that can efficiently support HBV infection . This finding will allow a deeper understanding of the requirements for efficient HBV infection , including the elucidation of the molecular entry mechanism . In addition , pharmacological studies suggest that NTCP is able to serve as a therapeutic target . This article summarizes our current knowledge on the mechanisms of HBV entry and the role of NTCP in this process . Int . J. Mol . Sci . 2014 , 15 2893\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Chronic hepatitis B virus ( HBV ) infection ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"affecting approximately 240 million people worldwide ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"is a major public health problem that elevates the risk of developing liver cirrhosis and hepatocellular carcinoma .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Given that current anti-HBV drugs are limited to interferon-based regimens and nucleos ( t ) ide analogs ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"the development of new anti-HBV agents is urgently needed .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"The viral entry process is generally an attractive target implicated in antiviral strategies .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Using primary cells from humans and Tupaia belangeri ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"as well as HepaRG cells ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"important determinants of viral entry have been achieved .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"Recently , sodium taurocholate cotransporting polypeptide ( NTCP ) was identified as an HBV entry receptor and enabled the establishment of a susceptible cell line that can efficiently support HBV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"This finding will allow a deeper understanding of the requirements for efficient HBV infection ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"including the elucidation of the molecular entry mechanism .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"In addition , pharmacological studies suggest that NTCP is able to serve as a therapeutic target .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"This article summarizes our current knowledge on the mechanisms of HBV entry and the role of NTCP in this process .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Int .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 15}, {\"segment_text\": \"J. Mol .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 16}, {\"segment_text\": \"Sci .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 17}, {\"segment_text\": \"2014 , 15 2893\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 18}]}"}]}
{"paper_id": "cc64e47ceb8557822f53767880c303eded7b0225", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nsubsequently led to an earlier disease onset and more severe clinical and histological signs of demyelinating disease . Our results have important implications for understanding the pathogenesis of MS , and suggest that stressful events during early infection with an agent capable of inducing demyelination may result in immunosuppression and failure to eliminate the pathogen , which in turn may lead to the development of MS. Multiple sclerosis ( MS ) is the most common demyelinating disease of the central nervous system ( CNS ) affecting approximately 350,000 people in the US . The etiology of this disease is unknown , although viral infection during early adulthood is suspected as an initiating event followed by autoimmune-mediated demyelination . In common with other autoimmune diseases , stressful life events precipitate both the onset and clinical relapses in MS patients . One of the mechanisms by which stress affects MS is to compromise the immune system and lead to increased susceptibility to infections , Psychological stress is an important factor in susceptibility to many diseases . Our laboratory has been investigating the impact of stress on the susceptibility to Theiler 's virusinduced demyelination ( TVID ) , a mouse model of multiple sclerosis . Using immunodominant viral peptides specific for identification of either CD4 + or CD8 + T cells , stress reduced IFN - ␥ - producing virus-specific CD4 + and CD8 + T cells in the spleen and CD8 + T cells in the CNS . Expression of mRNA for the Th1 transcription factor T-bet and the Th2 transcription factor GATA-3 were decreased in spleen cells isolated from stressed mice . Cytokine production by cells isolated from the CNS or spleens following stimulation with virus indicated that stress decreased both type 1 and type 2 responses . The adverse effects of stress were partially reversed by concurrent RU486 administration but mimicked by dexamethasone , indicating a major role for glucocorticoids . Global stress-induced immunosuppression resulted in higher levels of virus replication and dissemination . The higher viral load\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"subsequently led to an earlier disease onset and more severe clinical and histological signs of demyelinating disease .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Our results have important implications for understanding the pathogenesis of MS ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"and suggest that stressful events during early infection with an agent capable of inducing demyelination may result in immunosuppression and failure to eliminate the pathogen ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"which in turn may lead to the development of MS.\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Multiple sclerosis ( MS ) is the most common demyelinating disease of the central nervous system ( CNS ) affecting approximately 350,000 people in the US .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"The etiology of this disease is unknown ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"although viral infection during early adulthood is suspected as an initiating event followed by autoimmune-mediated demyelination .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"In common with other autoimmune diseases ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"stressful life events precipitate both the onset and clinical relapses in MS patients .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"One of the mechanisms by which stress affects MS is to compromise the immune system and lead to increased susceptibility to infections ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"Psychological stress is an important factor in susceptibility to many diseases .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"Our laboratory has been investigating the impact of stress on the susceptibility to Theiler 's virusinduced demyelination ( TVID ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"a mouse model of multiple sclerosis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}, {\"segment_text\": \"Using immunodominant viral peptides specific for identification of either CD4 + or CD8 + T cells ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"stress reduced IFN - ␥ - producing virus-specific CD4 + and CD8 + T cells in the spleen and CD8 + T cells in the CNS .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 15}, {\"segment_text\": \"Expression of mRNA for the Th1 transcription factor T-bet and the Th2 transcription factor GATA-3 were decreased in spleen cells isolated from stressed mice .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Cytokine production by cells isolated from the CNS or spleens following stimulation with virus indicated that stress decreased both type 1 and type 2 responses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"The adverse effects of stress were partially reversed by concurrent RU486 administration but mimicked by dexamethasone ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"indicating a major role for glucocorticoids .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Global stress-induced immunosuppression resulted in higher levels of virus replication and dissemination .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"The higher viral load\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}]}"}]}
{"paper_id": "7e92385d74e531617394983f187f6b4c9ca2f328", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMusk of musk deer has been one of the most precious traditional medicinal materials for treatment of stroke , but trading is prohibited . Musk of muskrat , Ondatra zibethicus , is an accessible substitute for musk of musk deer . However , neuroprotective effects of the musk of muskrat on stroke model are so far unclear . Aim of the study is to determine neuroprotective effects of the musk of muskrat on focal cerebral ischemia . The protective effects against focal cerebral ischemia were evaluated using a model of middle cerebral artery occlusion ( 90-minute occlusion followed by 24-hour reperfusion ) . Musk of muskrat was collected from scent bag of muskrat and orally administered at doses of 100 and 300 mg/kg twice at times of 0 and 90 min after occlusion . The effects on sensorimotor dysfunction were investigated by using balance beam test and rotarod test after brain ischemia . The expression of cyclooxygenase-2 ( COX-2 ) was investigated by immunohistochemistry . Oral administration of musk at 300 mg/kg significantly reduced ( p < 0.001 ) the infarct volume by 32.4 % compared with a vehicle-treated group . Oral administration of musk at 300 mg/kg also ameliorated ischemia-induced spontaneous and vestibule sensorimotor dysfunction in balance beam test and rotarod test compared with control group and COX-2 upregulation . Musk of muskrat may have neuroprotective effects against transient focal cerebral ischemia with recovery of sensorimotor dysfunction . Regarding the immunohistochemistry , the effects of muskrat may be due to anti-inflammatory properties through inhibition of COX-2 expressions .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Musk of musk deer has been one of the most precious traditional medicinal materials for treatment of stroke , but trading is prohibited .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Musk of muskrat , Ondatra zibethicus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"is an accessible substitute for musk of musk deer .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"However , neuroprotective effects of the musk of muskrat on stroke model are so far unclear .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Aim of the study is to determine neuroprotective effects of the musk of muskrat on focal cerebral ischemia .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"The protective effects against focal cerebral ischemia were evaluated using a model of middle cerebral artery occlusion ( 90-minute occlusion followed by 24-hour reperfusion ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Musk of muskrat was collected from scent bag of muskrat and orally administered at doses of 100 and 300 mg/kg twice at times of 0 and 90 min after occlusion .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"The effects on sensorimotor dysfunction were investigated by using balance beam test and rotarod test after brain ischemia .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The expression of cyclooxygenase-2 ( COX-2 ) was investigated by immunohistochemistry .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Oral administration of musk at 300 mg/kg significantly reduced ( p < 0.001 ) the infarct volume by 32.4 % compared with a vehicle-treated group .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Oral administration of musk at 300 mg/kg also ameliorated ischemia-induced spontaneous and vestibule sensorimotor dysfunction in balance beam test and rotarod test compared with control group and COX-2 upregulation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Musk of muskrat may have neuroprotective effects against transient focal cerebral ischemia with recovery of sensorimotor dysfunction .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Regarding the immunohistochemistry , the effects of muskrat may be due to anti-inflammatory properties through inhibition of COX-2 expressions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "6fccba98b953f6f90decbf7e76a279f47f6a372b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nWhile general medical practitioners ( GPs ) and veterinarians are often the first line responders in the face of a disease outbreak , pathways to improving the One Health efficacy of these clinicians remain unclear . A two-phase modified Delphi survey of professionals with known expertise in One Health ( ` expert panel ' ) was used to 1 ) identify key knowledge , attitudes and practices ( KAPs ) of GPs and veterinarians that would be consistent with a One Health approach to zoonoses ; and 2 ) determine priorities for future surveys with Australian GPs and veterinarians to identify important gaps that impede effective diagnosis and management of zoonoses . A list of 13 topics/sub-topics , as well as a list of 25 specific zoonotic diseases/agents emerged from the first phase of the survey . In the second phase the expert panel identified general knowledge of the clinical aspects and epidemiological aspects of zoonoses , as well as risk management practices , as the most important KAPs and research priorities for both GPs and veterinarians . In terms of diseases , the expert panel regarded knowledge of Hendra virus , Q fever , Australian bat lyssavirus ( ABLV ) , anthrax and Brucella suis most important for veterinarians , whilst for GPs , Q fever , gastrointestinal/foodborne diseases , influenza , ABLV and local vector-borne diseases were found to be most important by the expert panel . Some differences were noted in terms of prioritization of topics/sub-topics and diseases/agents according to expert background ( veterinary and non-veterinary ) . The Delphi survey technique enabled efficient collection of data from a diverse range of One Health ` experts ' / specialists and provided clear priorities for proposed future research , and potentially for educational interventions to improve One Health efficacy of clinicians .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"While general medical practitioners ( GPs ) and veterinarians are often the first line responders in the face of a disease outbreak ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"pathways to improving the One Health efficacy of these clinicians remain unclear .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"A two-phase modified Delphi survey of professionals with known expertise in One Health ( ` expert panel ' ) was used to 1 ) identify key knowledge ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"attitudes and practices ( KAPs ) of GPs and veterinarians that would be consistent with a One Health approach to zoonoses ; and 2 ) determine priorities for future surveys with Australian GPs and veterinarians to identify important gaps that impede effective diagnosis and management of zoonoses .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"A list of 13 topics/sub-topics ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"as well as a list of 25 specific zoonotic diseases/agents emerged from the first phase of the survey .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"In the second phase the expert panel identified general knowledge of the clinical aspects and epidemiological aspects of zoonoses ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"as well as risk management practices ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"as the most important KAPs and research priorities for both GPs and veterinarians .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"In terms of diseases , the expert panel regarded knowledge of Hendra virus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Q fever , Australian bat lyssavirus ( ABLV ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"anthrax and Brucella suis most important for veterinarians ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"whilst for GPs , Q fever ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"gastrointestinal/foodborne diseases , influenza , ABLV and local vector-borne diseases were found to be most important by the expert panel .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Some differences were noted in terms of prioritization of topics/sub-topics and diseases/agents according to expert background ( veterinary and non-veterinary ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"The Delphi survey technique enabled efficient collection of data from a diverse range of One Health ` experts ' / specialists and provided clear priorities for proposed future research ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"and potentially for educational interventions to improve One Health efficacy of clinicians .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "ecf2675fbb7883ca4a8f98c34eadb55c6b857aaa", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAs one of the most important post-translational modifications , ubiquitination plays versatile roles in cancer-related pathways , and is involved in protein metabolism , cell-cycle progression , apoptosis , and transcription . Counteracting the activities of the E3 ligases , the deubiquitylating enzymes have been suggested as another important mechanism to modulate the ubiquitination process , and are implicated in cancer as well . In this article , we review the emerging roles of USP28 in cancer pathways as revealed by recent studies . We discuss the major mechanisms by which USP28 is involved in the cancer-related pathways , whereby USP28 regulates physiological homeostasis of ubiquitination process , DNA-damage response , and cell cycle during genotoxic stress . We further review the studies where USP28 was targeted for treating multiples cancers including non-small cell lung cancer , breast cancer , intestinal cancers , gliomas , and bladder cancer . As a result , the clinical significance of targeting USP28 for cancer therapy merits further exploration and demonstration . • In addition to developing pharmacological inhibitors of USP28 , what are other efficient strategies of targeting USP28 that have clinical adaptability and feasibility for treating cancers ?\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"As one of the most important post-translational modifications ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"ubiquitination plays versatile roles in cancer-related pathways ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"and is involved in protein metabolism ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"cell-cycle progression , apoptosis , and transcription .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Counteracting the activities of the E3 ligases ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"the deubiquitylating enzymes have been suggested as another important mechanism to modulate the ubiquitination process ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"and are implicated in cancer as well .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"In this article , we review the emerging roles of USP28 in cancer pathways as revealed by recent studies .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"We discuss the major mechanisms by which USP28 is involved in the cancer-related pathways ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}, {\"segment_text\": \"whereby USP28 regulates physiological homeostasis of ubiquitination process ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 10}, {\"segment_text\": \"DNA-damage response , and cell cycle during genotoxic stress .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 11}, {\"segment_text\": \"We further review the studies where USP28 was targeted for treating multiples cancers including non-small cell lung cancer ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}, {\"segment_text\": \"breast cancer , intestinal cancers ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 13}, {\"segment_text\": \"gliomas , and bladder cancer .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 14}, {\"segment_text\": \"As a result , the clinical significance of targeting USP28 for cancer therapy merits further exploration and demonstration .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"• In addition to developing pharmacological inhibitors of USP28 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"what are other efficient strategies of targeting USP28 that have clinical adaptability and feasibility for treating cancers ?\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}]}"}]}
{"paper_id": "399cef5a5c8ca96a0ac33ee31dec722eac145a7b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nKnowledge of the distribution and diversity of RNA viruses is still limited in spite of their possible environmental and epidemiological impacts because RNA virus-specific metagenomic methods have not yet been developed . We herein constructed an effective metagenomic method for RNA viruses by targeting long double-stranded ( ds ) RNA in cellular organisms , which is a hallmark of infection , or the replication of dsRNA and single-stranded ( ss ) RNA viruses , except for retroviruses . This novel dsRNA targeting metagenomic method is characterized by an extremely high recovery rate of viral RNA sequences , the retrieval of terminal sequences , and uniform read coverage , which has not previously been reported in other metagenomic methods targeting RNA viruses . This method revealed a previously unidentified viral RNA diversity of more than 20 complete RNA viral genomes including dsRNA and ssRNA viruses associated with an environmental diatom colony . Our approach will be a powerful tool for cataloging RNA viruses associated with organisms of interest .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Knowledge of the distribution and diversity of RNA viruses is still limited in spite of their possible environmental and epidemiological impacts because RNA virus-specific metagenomic methods have not yet been developed .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"We herein constructed an effective metagenomic method for RNA viruses by targeting long double-stranded ( ds ) RNA in cellular organisms ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"which is a hallmark of infection ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"or the replication of dsRNA and single-stranded ( ss ) RNA viruses , except for retroviruses .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"This novel dsRNA targeting metagenomic method is characterized by an extremely high recovery rate of viral RNA sequences ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"the retrieval of terminal sequences ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"and uniform read coverage , which has not previously been reported in other metagenomic methods targeting RNA viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"This method revealed a previously unidentified viral RNA diversity of more than 20 complete RNA viral genomes including dsRNA and ssRNA viruses associated with an environmental diatom colony .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Our approach will be a powerful tool for cataloging RNA viruses associated with organisms of interest .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}]}"}]}
{"paper_id": "43918c75d7b7d3f9402b1342dfea1e19eb2bd909", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe bactericidal activity of conventional titanium dioxide ( TiO 2 ) photocatalyst is effective only on irradiation by ultraviolet light , which restricts the applications of TiO 2 for use in living environments . Recently , carbon-containing TiO 2 nanoparticles ( TiO 2 ( C ) NP ) were found to be a visible-light-responsive photocatalyst ( VLRP ) , which displayed significantly enhanced antibacterial properties under visible light illumination . However , whether TiO 2 ( C ) NPs exert antibacterial properties against Bacillus anthracis remains elusive . Here , we evaluated these VLRP NPs in the reduction of anthrax-induced pathogenesis . Bacteria-killing experiments indicated that a significantly higher proportion ( 40 % -60 % ) of all tested Bacillus species , including B. subtilis , B. cereus , B. thuringiensis , and B. anthracis , were considerably eliminated by TiO 2 ( C ) NPs . Toxin inactivation analysis further suggested that the TiO 2 ( C ) NPs efficiently detoxify approximately 90 % of tested anthrax lethal toxin , a major virulence factor of anthrax . Notably , macrophage clearance experiments further suggested that , even under suboptimal conditions without considerable bacterial killing , the TiO 2 ( C ) NP-mediated photocatalysis still exhibited antibacterial properties through the reduction of bacterial resistance against macrophage killing . Our results collectively suggested that TiO 2 ( C ) NP is a conceptually feasible anti-anthrax material , and the relevant technologies described herein may be useful in the development of new strategies against anthrax .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The bactericidal activity of conventional titanium dioxide ( TiO 2 ) photocatalyst is effective only on irradiation by ultraviolet light ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"which restricts the applications of TiO 2 for use in living environments .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Recently , carbon-containing TiO 2 nanoparticles ( TiO 2 ( C ) NP ) were found to be a visible-light-responsive photocatalyst ( VLRP ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"which displayed significantly enhanced antibacterial properties under visible light illumination .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"However , whether TiO 2 ( C ) NPs exert antibacterial properties against Bacillus anthracis remains elusive .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Here , we evaluated these VLRP NPs in the reduction of anthrax-induced pathogenesis .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"Bacteria-killing experiments indicated that a significantly higher proportion ( 40 % -60 % ) of all tested Bacillus species ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"including B. subtilis , B. cereus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"B. thuringiensis , and B. anthracis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"were considerably eliminated by TiO 2 ( C ) NPs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Toxin inactivation analysis further suggested that the TiO 2 ( C ) NPs efficiently detoxify approximately 90 % of tested anthrax lethal toxin ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"a major virulence factor of anthrax .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Notably , macrophage clearance experiments further suggested that ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"even under suboptimal conditions without considerable bacterial killing ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"the TiO 2 ( C ) NP-mediated photocatalysis still exhibited antibacterial properties through the reduction of bacterial resistance against macrophage killing .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Our results collectively suggested that TiO 2 ( C ) NP is a conceptually feasible anti-anthrax material ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"and the relevant technologies described herein may be useful in the development of new strategies against anthrax .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}]}"}]}
{"paper_id": "0150b2d0c4f75faf01a869d3f5109fca50aab5c3", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe co-evolution of viruses with their hosts has led to the emergence of viral pathogens that are adept at evading or actively suppressing host immunity . Pattern recognition receptors ( PRRs ) are key components of antiviral immunity that detect conserved molecular features of viral pathogens and initiate signalling that results in the expression of antiviral genes . In this Review , we discuss the strategies that viruses use to escape immune surveillance by key intracellular sensors of viral RNA or DNA , with a focus on RIG-I-like receptors ( RLRs ) , cyclic GMP-AMP synthase ( cGAS ) and interferon-γ ( IFNγ ) - inducible protein 16 ( IFI16 ) . Such viral strategies include the sequestration or modification of viral nucleic acids , interference with specific post-translational modifications of PRRs or their adaptor proteins , the degradation or cleavage of PRRs or their adaptors , and the sequestration or relocalization of PRRs . An understanding of viral immuneevasion mechanisms at the molecular level may guide the development of vaccines and antivirals .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The co-evolution of viruses with their hosts has led to the emergence of viral pathogens that are adept at evading or actively suppressing host immunity .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Pattern recognition receptors ( PRRs ) are key components of antiviral immunity that detect conserved molecular features of viral pathogens and initiate signalling that results in the expression of antiviral genes .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"In this Review , we discuss the strategies that viruses use to escape immune surveillance by key intracellular sensors of viral RNA or DNA ,\", \"label\": \"purpose\", \"decision_reference\": \"boundary background_vs_purpose\", \"id\": 3}, {\"segment_text\": \"with a focus on RIG-I-like receptors ( RLRs ) ,\", \"label\": \"purpose\", \"decision_reference\": \"boundary background_vs_purpose\", \"id\": 4}, {\"segment_text\": \"cyclic GMP-AMP synthase ( cGAS ) and interferon-γ ( IFNγ ) - inducible protein 16 ( IFI16 ) .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Such viral strategies include the sequestration or modification of viral nucleic acids ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"interference with specific post-translational modifications of PRRs or their adaptor proteins ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"the degradation or cleavage of PRRs or their adaptors ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"and the sequestration or relocalization of PRRs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"An understanding of viral immuneevasion mechanisms at the molecular level may guide the development of vaccines and antivirals .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "df0c41998e31603d157707d4acfc7bad63e0afd7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nA sensitive and specific method for the diagnosis of infectious bronchitis virus ( IBV ) is of great importance . In this study the development of a real-time TaqMan ® RT-PCR targeting the highly conserved nucleocapsid ( N ) gene of IBV and including an internal PCR control is described . The assay was specific for IBV and did not detect other avian pathogens , including turkey coronaviruses . A comparative limit of detection was determined for M41 , an embryo-adapted strain , and IS/885/00 , a poorly embryo-adapted variant . For M41 real-time RT-PCR and virus isolation were one or two times more sensitive than RT-PCR targeting the N or spike glycoprotein ( S1 ) genes , respectively . For IS/885/00 , real-time RT-PCR was more sensitive by tenfold than virus isolation and 30-or 40-fold than by N gene or S1 gene RT-PCR , respectively . Real-time RT-PCR and virus isolation were 17-75 % more sensitive than RT-PCR targeting the S1 gene for testing tracheal swabs directly from experimentally infected chicks . When tracheal and cloacal swabs from clinical specimens were tested directly , 50 % more samples were positive by real-time RT-PCR than by the S1 gene RT-PCR . Real-time RT-PCR targeting the N gene is more sensitive than common diagnostic assays , allowing rapid and accurate IBV detection directly from clinical specimens , facilitating differential diagnosis .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"A sensitive and specific method for the diagnosis of infectious bronchitis virus ( IBV ) is of great importance .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"In this study the development of a real-time TaqMan ® RT-PCR targeting the highly conserved nucleocapsid ( N ) gene of IBV and including an internal PCR control is described .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"The assay was specific for IBV and did not detect other avian pathogens , including turkey coronaviruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"A comparative limit of detection was determined for M41 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"an embryo-adapted strain , and IS/885/00 , a poorly embryo-adapted variant .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"For M41 real-time RT-PCR and virus isolation were one or two times more sensitive than RT-PCR targeting the N or spike glycoprotein ( S1 ) genes , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"For IS/885/00 , real-time RT-PCR was more sensitive by tenfold than virus isolation and 30-or 40-fold than by N gene or S1 gene RT-PCR , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Real-time RT-PCR and virus isolation were 17-75 % more sensitive than RT-PCR targeting the S1 gene for testing tracheal swabs directly from experimentally infected chicks .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"When tracheal and cloacal swabs from clinical specimens were tested directly ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"50 % more samples were positive by real-time RT-PCR than by the S1 gene RT-PCR .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Real-time RT-PCR targeting the N gene is more sensitive than common diagnostic assays ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"allowing rapid and accurate IBV detection directly from clinical specimens , facilitating differential diagnosis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "9df0801be110f632c616bf9e91cb72d59383b086", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nChina has implemented a free-service policy for tuberculosis . However , patients still have to pay a substantial proportion of their annual income for treatment of this disease . This study describes the economic burden on patients with tuberculosis ; identifies related factors by comparing two areas with different management models ; and provides policy recommendation for tuberculosis control reform in China . There are three tuberculosis management models in China : the tuberculosis dispensary model , specialist model and integrated model . We selected Zhangjiagang ( ZJG ) and Taixing ( TX ) as the study sites , which correspond to areas implementing the integrated model and dispensary model , respectively . Patients diagnosed and treated for tuberculosis since January 2010 were recruited as study subjects . A total of 590 patients ( 316 patients from ZJG and 274 patients from TX ) were interviewed with a response rate of 81 % . The economic burden attributed to tuberculosis , including direct costs and indirect costs , was estimated and compared between the two study sites . The Mann-Whitney U Test was used to compare the cost differences between the two groups . Potential factors related to the total outof-pocket costs were analyzed based on a step-by-step multivariate linear regression model after the logarithmic transformation of the costs . The average ( median , interquartile range ) total cost was 18793.33 ( 9965 , 3200-24400 ) CNY for patients in ZJG , which was significantly higher than for patients in TX ( mean : 6598.33 , median : 2263 , interquartile range : 983-6688 ) ( Z = 10.42 , P < 0.001 ) . After excluding expenses covered by health insurance , the average out-of-pocket costs were 14304.4 PLOS ONE | Education Institutions ( PAPD ) . The funders had no CNY in ZJG and 5639.2 CNY in TX . Based on the multivariable linear regression analysis , factors related to the total out-of-pocket costs were study site , age , number of clinical visits , residence , diagnosis delay , hospitalization , intake of liver protective drugs and use of the second-line drugs . Under the current `` free of diagnosis and treatment '' policy , the financial burden remains heavy on tuberculosis patients . Policy makers need to consider appropriate steps to lessen the burden of out-of-pocket costs for tuberculosis patients in China and how best to improve service delivery for poor patients . Economic Burden of TB PLOS ONE |\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"China has implemented a free-service policy for tuberculosis .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"However , patients still have to pay a substantial proportion of their annual income for treatment of this disease .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"This study describes the economic burden on patients with tuberculosis ; identifies related factors by comparing two areas with different management models ; and provides policy recommendation for tuberculosis control reform in China .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"There are three tuberculosis management models in China : the tuberculosis dispensary model ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"specialist model and integrated model .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"We selected Zhangjiagang ( ZJG ) and Taixing ( TX ) as the study sites ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"which correspond to areas implementing the integrated model and dispensary model , respectively .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Patients diagnosed and treated for tuberculosis since January 2010 were recruited as study subjects .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"A total of 590 patients ( 316 patients from ZJG and 274 patients from TX ) were interviewed with a response rate of 81 % .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"The economic burden attributed to tuberculosis ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"including direct costs and indirect costs ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"was estimated and compared between the two study sites .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"The Mann-Whitney U Test was used to compare the cost differences between the two groups .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Potential factors related to the total outof-pocket costs were analyzed based on a step-by-step multivariate linear regression model after the logarithmic transformation of the costs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"The average ( median , interquartile range ) total cost was 18793.33 ( 9965 , 3200-24400 ) CNY for patients in ZJG ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"which was significantly higher than for patients in TX ( mean : 6598.33 , median : 2263 , interquartile range : 983-6688 ) ( Z = 10.42 , P < 0.001 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"After excluding expenses covered by health insurance ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"the average out-of-pocket costs were 14304.4 PLOS ONE | Education Institutions ( PAPD ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"The funders had no CNY in ZJG and 5639.2 CNY in TX .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Based on the multivariable linear regression analysis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"factors related to the total out-of-pocket costs were study site ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"age , number of clinical visits ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"residence , diagnosis delay , hospitalization ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"intake of liver protective drugs and use of the second-line drugs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}, {\"segment_text\": \"Under the current `` free of diagnosis and treatment '' policy ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 25}, {\"segment_text\": \"the financial burden remains heavy on tuberculosis patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 26}, {\"segment_text\": \"Policy makers need to consider appropriate steps to lessen the burden of out-of-pocket costs for tuberculosis patients in China and how best to improve service delivery for poor patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 27}, {\"segment_text\": \"Economic Burden of TB PLOS ONE |\", \"label\": \"finding\", \"decision_reference\": \"other.rule\", \"id\": 28}]}"}]}
{"paper_id": "fb775c4af00b99294d4e8812a3f23ba6aca32774", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nZoonosis is the leading cause of emerging infectious diseases . In a recent article , R. S. Shabman et al. ( mSphere 1 ( 1 ) : e00070-15 , 2016 , 10.1128 report the identification of a novel gammaherpesvirus in a cell line derived from the microbat Myotis velifer incautus . This is the first report on a replicating , infectious gammaherpesvirus from bats . The new virus is named bat gammaherpesvirus 8 ( BGHV8 ) , also known as Myotis gammaherpesvirus 8 , and is able to infect multiple cell lines , including those of human origin . Using nextgeneration sequencing technology , the authors constructed a full-length annotated genomic map of BGHV8 . Phylogenetic analysis of several genes from BGHV8 revealed similarity to several mammalian gammaherpesviruses , including Kaposi 's sarcoma-associated herpesvirus ( KSHV ) . Citation Host KM , Damania B. 2016 . Discovery of a novel bat gammaherpesvirus . mSphere 1 ( 1 ) : e00016-16 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Zoonosis is the leading cause of emerging infectious diseases .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"In a recent article , R. S. Shabman et al. ( mSphere 1 ( 1 ) : e00070-15 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"2016 , 10.1128 report the identification of a novel gammaherpesvirus in a cell line derived from the microbat Myotis velifer incautus .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"This is the first report on a replicating , infectious gammaherpesvirus from bats .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"The new virus is named bat gammaherpesvirus 8 ( BGHV8 ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"also known as Myotis gammaherpesvirus 8 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"and is able to infect multiple cell lines ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"including those of human origin .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"Using nextgeneration sequencing technology , the authors constructed a full-length annotated genomic map of BGHV8 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Phylogenetic analysis of several genes from BGHV8 revealed similarity to several mammalian gammaherpesviruses ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"including Kaposi 's sarcoma-associated herpesvirus ( KSHV ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Citation Host KM , Damania B. 2016 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Discovery of a novel bat gammaherpesvirus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"mSphere 1 ( 1 ) : e00016-16 .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 14}]}"}]}
{"paper_id": "fad068abaa998641db5de8113fced6b3ef3d613f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPorphyromonas gulae is a major periodontal pathogen in dogs , which can be transmitted to their owners . A major virulence factor of P. gulae consists of a 41-kDa filamentous appendage ( FimA ) on the cell surface , which is classified into three genotypes : A , B , and C. Thus far , inhibition of periodontal disease in dogs remains difficult . The present study assessed the inhibitory effects of a combination of clindamycin and interferon alpha ( IFN-α ) formulation against P. gulae and periodontal disease . Growth of P. gulae was significantly inhibited by clindamycin ; this inhibition had a greater effect on type C P. gulae than on type A and B isolates . In contrast , the IFN-α formulation inhibited the expression of IL-1β and COX-2 elicited by type A and B isolates , but not that elicited by type C isolates . Furthermore , periodontal recovery was promoted by the administration of both clindamycin and ifn-α formulation to dogs undergoing periodontal treatment ; moreover , this combined treatment reduced the number of fimA genotypes in oral specimens from treated dogs . these results suggest that a combination of clindamycin and ifn-α formulation inhibit P. gulae virulence and thus may be effective for the prevention of periodontal disease induced by P. gulae .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Porphyromonas gulae is a major periodontal pathogen in dogs ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"which can be transmitted to their owners .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"A major virulence factor of P. gulae consists of a 41-kDa filamentous appendage ( FimA ) on the cell surface ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"which is classified into three genotypes : A ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"B , and C. Thus far ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"inhibition of periodontal disease in dogs remains difficult .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"The present study assessed the inhibitory effects of a combination of clindamycin and interferon alpha ( IFN-α ) formulation against P. gulae and periodontal disease .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"Growth of P. gulae was significantly inhibited by clindamycin ; this inhibition had a greater effect on type C P. gulae than on type A and B isolates .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"In contrast , the IFN-α formulation inhibited the expression of IL-1β and COX-2 elicited by type A and B isolates ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"but not that elicited by type C isolates .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Furthermore , periodontal recovery was promoted by the administration of both clindamycin and ifn-α formulation to dogs undergoing periodontal treatment ; moreover ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"this combined treatment reduced the number of fimA genotypes in oral specimens from treated dogs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"these results suggest that a combination of clindamycin and ifn-α formulation inhibit P. gulae virulence and thus may be effective for the prevention of periodontal disease induced by P. gulae .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}]}"}]}
{"paper_id": "4878d966944fb0b66d96fec7b7dff3f79194f26d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nInfluenza A virus ( IAV ) can infect host cells via pH-dependent endocytosis . It is generally accepted that hemagglutinin ( HA ) - mediated recognition of cell surface sialic acid ( SIA ) is the first step in initiating IAV infection , however surprisingly little is known regarding the identity of specific receptors and/or coreceptors that mediate virus internalization . SIA structures do not exhibit signalling capacity but may act as attachment factors , promoting interactions with specific transmembrane receptors for virus uptake . Alternatively , recognition of critical SIA residues expressed by transmembrane receptors may be required to initiate virus entry . As SIA-independent entry and infection has also been reported 1,2 , it is possible that some receptors can bind IAV and signal independently of SIA , although attachment to SIA may concentrate virions at the cell surface and augment this mode of entry . The sorting of IAV into particular entry pathways will be determined by specific adaptor protein ( s ) that bind to the cytoplasmic tails of IAV receptors and co-receptors , activating intracellular signalling proteins for subsequent internalization of virus . While little is known regarding the specific entry receptors for IAV expressed by epithelial cells , significant progress has been made towards identifying receptors that play a role in infectious entry of IAV into macrophages ( MΦ ) and dendritic cells ( DC ) . C-type lectin receptors ( CLRs ) are transmembrane glycoproteins that recognize glycans expressed on IAV glycoproteins and a number of distinct CLRs have been implicated in promoting IAV infection ( reviewed in 3 ) . Previous studies from our group implicated the macrophage mannose receptor ( MMR ) and the macrophage galactose-type lectin ( MGL ) -1 in infectious entry of IAV into mouse macrophages ( MΦ ) 4-6 . Of the human CLRs , expression of DC-SIGN ( DC209 ) and/or L-SIGN ( DC-SIGNR and CD209L ) by transfected cell lines 7-9 or primary cells 7,9 has also been associated with enhanced susceptibility to IAV infection . DC-SIGN and L-SIGN are tetrameric type II transmembrane CLRs expressing Ca 2 + - dependent ( C-type ) carbohydrate recognition domains ( CRD ) which bind preferentially to mannose-rich oligosaccharides ( reviewed in 10 ) . Despite their similarities , DC-SIGN and L-SIGN differ with respect to tissue distribution . DC-SIGN is expressed by MΦ and DC subsets throughout the body whereas L-SIGN tends to be expressed by non-immune cells . In the respiratory tract , DC-SIGN is expressed by human alveolar MΦ and subpopulations of lung DCs 11,12 , whereas L-SIGN is expressed by bronchiolar epithelial cells , type II alveolar cells and endothelial cells of the\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Influenza A virus ( IAV ) can infect host cells via pH-dependent endocytosis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"It is generally accepted that hemagglutinin ( HA ) - mediated recognition of cell surface sialic acid ( SIA ) is the first step in initiating IAV infection ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"however surprisingly little is known regarding the identity of specific receptors and/or coreceptors that mediate virus internalization .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"SIA structures do not exhibit signalling capacity but may act as attachment factors ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"promoting interactions with specific transmembrane receptors for virus uptake .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Alternatively , recognition of critical SIA residues expressed by transmembrane receptors may be required to initiate virus entry .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"As SIA-independent entry and infection has also been reported 1,2 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"it is possible that some receptors can bind IAV and signal independently of SIA ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"although attachment to SIA may concentrate virions at the cell surface and augment this mode of entry .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"The sorting of IAV into particular entry pathways will be determined by specific adaptor protein ( s ) that bind to the cytoplasmic tails of IAV receptors and co-receptors ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"activating intracellular signalling proteins for subsequent internalization of virus .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"While little is known regarding the specific entry receptors for IAV expressed by epithelial cells ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"significant progress has been made towards identifying receptors that play a role in infectious entry of IAV into macrophages ( MΦ ) and dendritic cells ( DC ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 13}, {\"segment_text\": \"C-type lectin receptors ( CLRs ) are transmembrane glycoproteins that recognize glycans expressed on IAV glycoproteins and a number of distinct CLRs have been implicated in promoting IAV infection ( reviewed in 3 ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 14}, {\"segment_text\": \"Previous studies from our group implicated the macrophage mannose receptor ( MMR ) and the macrophage galactose-type lectin ( MGL ) -1 in infectious entry of IAV into mouse macrophages ( MΦ ) 4-6 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 15}, {\"segment_text\": \"Of the human CLRs , expression of DC-SIGN ( DC209 ) and/or L-SIGN ( DC-SIGNR and CD209L ) by transfected cell lines 7-9 or primary cells 7,9 has also been associated with enhanced susceptibility to IAV infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 16}, {\"segment_text\": \"DC-SIGN and L-SIGN are tetrameric type II transmembrane CLRs expressing Ca 2 + - dependent ( C-type ) carbohydrate recognition domains ( CRD ) which bind preferentially to mannose-rich oligosaccharides ( reviewed in 10 ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 17}, {\"segment_text\": \"Despite their similarities , DC-SIGN and L-SIGN differ with respect to tissue distribution .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 18}, {\"segment_text\": \"DC-SIGN is expressed by MΦ and DC subsets throughout the body whereas L-SIGN tends to be expressed by non-immune cells .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 19}, {\"segment_text\": \"In the respiratory tract , DC-SIGN is expressed by human alveolar MΦ and subpopulations of lung DCs 11,12 ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 20}, {\"segment_text\": \"whereas L-SIGN is expressed by bronchiolar epithelial cells ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 21}, {\"segment_text\": \"type II alveolar cells and endothelial cells of the\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 22}]}"}]}
{"paper_id": "9faf6a32a170b3fc5950af6a7d34cf710c79321d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Human influenza virus hemagglutinin prefers to use sialic acid ( SA ) receptors via α-2,6 linkages . The β-galactoside α-2,6-sialyltransferase I ( ST6Gal I ) protein is encoded by the ST6GAL1 gene and is responsible for the addition of α-2,6 linked SA to the Galβ1-4GlcNAc disaccharide of glycans and glycoproteins found on the cellular surface . Therefore , ST6GAL1 could be a potential target for anti-influenza therapeutics . We used specific small interfering RNAs ( siRNAs ) to block expression of ST6GAL1 and limit distribution of SA receptors on the surface of airway epithelial cells . Results : The siRNA duplexes we used inhibited ST6GAL1 mRNA expression and subsequent expression of the encoding protein . As a result , synthesis of α-2,6 SA galactose was inhibited . Adsorption of influenza virus particles to the surface of cells transfected with appropriate specific siRNAs was significantly reduced . Intracellular viral genome copy number and virus titer within the supernatant of cells transfected with siRNAs was significantly reduced in a dose-dependent manner compared with those for untransfected cells and cells transfected with non-specific siRNAs . Conclusions : We used siRNAs targeting ST6GAL1 to inhibit the expression of certain cell surface receptors , thereby preventing virus adsorption . This resulted in the inhibition of human influenza virus infection . Our findings are a significant development in the identification of potential new anti-influenza drug targets .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Human influenza virus hemagglutinin prefers to use sialic acid ( SA ) receptors via α-2,6 linkages .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The β-galactoside α-2,6-sialyltransferase I ( ST6Gal I ) protein is encoded by the ST6GAL1 gene and is responsible for the addition of α-2,6 linked SA to the Galβ1-4GlcNAc disaccharide of glycans and glycoproteins found on the cellular surface .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Therefore , ST6GAL1 could be a potential target for anti-influenza therapeutics .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"We used specific small interfering RNAs ( siRNAs ) to block expression of ST6GAL1 and limit distribution of SA receptors on the surface of airway epithelial cells .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Results : The siRNA duplexes we used inhibited ST6GAL1 mRNA expression and subsequent expression of the encoding protein .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"As a result , synthesis of α-2,6 SA galactose was inhibited .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Adsorption of influenza virus particles to the surface of cells transfected with appropriate specific siRNAs was significantly reduced .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Intracellular viral genome copy number and virus titer within the supernatant of cells transfected with siRNAs was significantly reduced in a dose-dependent manner compared with those for untransfected cells and cells transfected with non-specific siRNAs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Conclusions : We used siRNAs targeting ST6GAL1 to inhibit the expression of certain cell surface receptors , thereby preventing virus adsorption .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"This resulted in the inhibition of human influenza virus infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Our findings are a significant development in the identification of potential new anti-influenza drug targets .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}]}"}]}
{"paper_id": "5ed927af9278b000ed188d0d20c6e11f041e7937", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAims : This paper aims to summarise the growing literature concerning an imminent future influenza pandemic , from the primary care perspective . Methods : Sources of literature were scanned and relevant material short-listed for further study from : ( 1 ) WHO and CDC websites ; ( 2 ) PUBMED ; and ( 3 ) papers mentioned in references of full-text papers . Results : Outbreaks of avian influenza in Asia and elsewhere indicate that the world may be moving towards a pandemic influenza outbreak . The WHO Global Influenza Preparedness Plan 2005 unifies the world with the vision of tackling the next pandemic influenza outbreak as a global effort that includes healthcare provider and patient alike . Conclusions : We need to update ourselves and keep our staff and patients informed to make infection control measures part of our daily activities . In areas where there are contacts with animal reservoirs of influenza A , patients need to be reminded that they need to protect themselves from being infected .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Aims : This paper aims to summarise the growing literature concerning an imminent future influenza pandemic ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"from the primary care perspective .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"Methods : Sources of literature were scanned and relevant material short-listed for further study from : ( 1 ) WHO and CDC websites ; ( 2 ) PUBMED ; and ( 3 ) papers mentioned in references of full-text papers .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Results : Outbreaks of avian influenza in Asia and elsewhere indicate that the world may be moving towards a pandemic influenza outbreak .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 4}, {\"segment_text\": \"The WHO Global Influenza Preparedness Plan 2005 unifies the world with the vision of tackling the next pandemic influenza outbreak as a global effort that includes healthcare provider and patient alike .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"Conclusions : We need to update ourselves and keep our staff and patients informed to make infection control measures part of our daily activities .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"In areas where there are contacts with animal reservoirs of influenza A ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"patients need to be reminded that they need to protect themselves from being infected .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}]}"}]}
{"paper_id": "fbabb5fb318eb82681d448718a79bc44f11a7643", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nEmerging Infectious Diseases • www.cdc.gov/eid • Vol . 10 , No. 2 , February 2004 255 RESEARCH SARS TRANSMISSION Figure . Onset of symptoms for severe acute respiratory syndrome by number of shifts worked ( dashed lines represent 95 % confidence limits ) .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Emerging Infectious Diseases • www.cdc.gov/eid • Vol .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 1}, {\"segment_text\": \"10 , No. 2 , February 2004 255 RESEARCH SARS TRANSMISSION Figure .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Onset of symptoms for severe acute respiratory syndrome by number of shifts worked ( dashed lines represent 95 % confidence limits ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}]}"}]}
{"paper_id": "f7a3c341035528c458ca916e3daeb47645da212b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nNext generation sequencing ( NGS ) technologies have revolutionized the genomics field and are becoming more commonplace for identification of human infectious diseases . However , due to the low abundance of viral nucleic acids ( NAs ) in relation to host , viral identification using direct NGS technologies often lacks sufficient sensitivity . Here , we describe an approach based on two complementary enrichment strategies that significantly improves the sensitivity of NGS-based virus identification . To start , we developed two sets of DNA probes to enrich virus NAs associated with respiratory diseases . The first set of probes spans the genomes , allowing for identification of known viruses and full genome sequencing , while the second set targets regions conserved among viral families or genera , providing the ability to detect both known and potentially novel members of those virus groups . Efficiency of enrichment was assessed by NGS testing reference virus and clinical samples with known infection . We show significant improvement in viral identification using enriched NGS compared to unenriched NGS . Without enrichment , we observed an average of 0.3 % targeted viral reads per sample . However , after enrichment , 50 % -99 % of the reads per sample were the targeted viral reads for both the reference isolates and clinical specimens using both probe sets . Importantly , dramatic improvements on genome coverage were also observed following virus-specific probe enrichment . The methods described here provide improved sensitivity for virus identification by NGS , allowing for a more comprehensive analysis of disease etiology .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Next generation sequencing ( NGS ) technologies have revolutionized the genomics field and are becoming more commonplace for identification of human infectious diseases .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"However , due to the low abundance of viral nucleic acids ( NAs ) in relation to host ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"viral identification using direct NGS technologies often lacks sufficient sensitivity .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Here , we describe an approach based on two complementary enrichment strategies that significantly improves the sensitivity of NGS-based virus identification .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"To start , we developed two sets of DNA probes to enrich virus NAs associated with respiratory diseases .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"The first set of probes spans the genomes ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"allowing for identification of known viruses and full genome sequencing ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"while the second set targets regions conserved among viral families or genera ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"providing the ability to detect both known and potentially novel members of those virus groups .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Efficiency of enrichment was assessed by NGS testing reference virus and clinical samples with known infection .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"We show significant improvement in viral identification using enriched NGS compared to unenriched NGS .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Without enrichment , we observed an average of 0.3 % targeted viral reads per sample .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"However , after enrichment , 50 % -99 % of the reads per sample were the targeted viral reads for both the reference isolates and clinical specimens using both probe sets .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Importantly , dramatic improvements on genome coverage were also observed following virus-specific probe enrichment .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"The methods described here provide improved sensitivity for virus identification by NGS ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"allowing for a more comprehensive analysis of disease etiology .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "1954505b8d34d065e8140c40db252d0e21fe4bb0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nFoot-and-mouth disease virus ( FMDV ) is the type species of the Aphthovirus genus within the Picornaviridae family . Infection of cells with positive-strand RNA viruses results in a rearrangement of intracellular membranes into viral replication complexes . The origin of these membranes remains unknown ; however induction of the cellular process of autophagy is beneficial for the replication of poliovirus , suggesting that it might be advantageous for other picornaviruses . By using confocal microscopy we showed in FMDV-infected cells co-localization of non-structural viral proteins 2B , 2C and 3A with LC3 ( an autophagosome marker ) and viral structural protein VP1 with Atg5 ( autophagy-related protein ) , and LC3 with LAMP-1 . Importantly , treatment of FMDV-infected cell with autophagy inducer rapamycin , increased viral yield , and inhibition of autophagosomal pathway by 3-methyladenine or small-interfering RNAs , decreased viral replication . Altogether , these studies strongly suggest that autophagy may play an important role during the replication of FMDV . Published by Elsevier Inc. . Virology 410 ( 2011 ) 142-150\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Foot-and-mouth disease virus ( FMDV ) is the type species of the Aphthovirus genus within the Picornaviridae family .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Infection of cells with positive-strand RNA viruses results in a rearrangement of intracellular membranes into viral replication complexes .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The origin of these membranes remains unknown ; however induction of the cellular process of autophagy is beneficial for the replication of poliovirus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"suggesting that it might be advantageous for other picornaviruses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"By using confocal microscopy we showed in FMDV-infected cells co-localization of non-structural viral proteins 2B ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"2C and 3A with LC3 ( an autophagosome marker ) and viral structural protein VP1 with Atg5 ( autophagy-related protein ) , and LC3 with LAMP-1 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Importantly , treatment of FMDV-infected cell with autophagy inducer rapamycin ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"increased viral yield , and inhibition of autophagosomal pathway by 3-methyladenine or small-interfering RNAs , decreased viral replication .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Altogether , these studies strongly suggest that autophagy may play an important role during the replication of FMDV .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Published by Elsevier Inc. .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 10}, {\"segment_text\": \"Virology 410 ( 2011 ) 142-150\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 11}]}"}]}
{"paper_id": "aea1136bae15d1d3b628f228145f6853578f2b55", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRespiratory syncytial virus ( RSV ) is the most frequently identified viral agent in infants , children , and elderly people with acute respiratory tract infections ( ARTIs ) . This study is the only one of its kind in Kuwait , and its purpose was to investigate the genetic variability of the G protein gene in RSV strains prevalent in Kuwait . Respiratory samples were collected from patients with ARTIs in various hospitals in Kuwait and subjected to reverse transcription PCR ( RT-PCR ) amplifying a fragment of the G gene of RSV . A total of 305 samples were collected between January and mid-December 2016 , and 77 ( 25.2 % ) were positive for RSV . Group A viruses were predominant over group B viruses ; the RSV-A group was detected in 52 ( 67.5 % ) of the positive samples , while the RSV-B group was detected in 25 ( 32.5 % ) of the positive samples . Phylogenetic analysis showed that all RSV-A strains grouped into eight clusters of identical sequences of untyped strains . Twelve RSV-B strains , on the other hand , belonged to the RSV-B/BA10 genotype , while the rest were untyped . These data suggest that new and untyped strains of RSV-A group likely predominated in Kuwait and that the BA10 genotype of the RSV-B group became the dominant genotype in the 2016 season .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Respiratory syncytial virus ( RSV ) is the most frequently identified viral agent in infants ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"children , and elderly people with acute respiratory tract infections ( ARTIs ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"This study is the only one of its kind in Kuwait ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"and its purpose was to investigate the genetic variability of the G protein gene in RSV strains prevalent in Kuwait .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Respiratory samples were collected from patients with ARTIs in various hospitals in Kuwait and subjected to reverse transcription PCR ( RT-PCR ) amplifying a fragment of the G gene of RSV .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"A total of 305 samples were collected between January and mid-December 2016 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"and 77 ( 25.2 % ) were positive for RSV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Group A viruses were predominant over group B viruses ; the RSV-A group was detected in 52 ( 67.5 % ) of the positive samples ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"while the RSV-B group was detected in 25 ( 32.5 % ) of the positive samples .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Phylogenetic analysis showed that all RSV-A strains grouped into eight clusters of identical sequences of untyped strains .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"Twelve RSV-B strains , on the other hand ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"belonged to the RSV-B/BA10 genotype ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"while the rest were untyped .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"These data suggest that new and untyped strains of RSV-A group likely predominated in Kuwait and that the BA10 genotype of the RSV-B group became the dominant genotype in the 2016 season .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "09e70c44b20fc3618bdc374ebd82d72795941b2d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nTo determine the factors that predict in-hospital mortality among patients who require hospitalization for the treatment of community-acquired pneumonia ( CAP ) . Study design : Prospective observational study of all patients who were admitted to six hospitals in Edmonton , AL , Canada , with a diagnosis of CAP from November 15 , 2000 , to November 14 , 2002 . Pneumonia was defined as two or more respiratory symptoms and signs and an opacity on a chest radiograph as interpreted by the attending physician . Results : A total of 3,043 patients were enrolled in the study , 246 of whom died ( 8.1 % ) . On multivariate analysis , increasing pneumonia severity score , increasing age , site of care , consultation with a respirologist or infectious diseases physician , and functional status at the time of admission were all independently predictive of mortality . Increasing pneumonia severity risk score , increasing age , site of hospitalization , functional status , and consultation with an infectious diseases physician or a respirologist were independently associated with both early ( < 5 days ) and late ( > 5 days ) mortality . In contrast , partial or complete use of the pneumonia pathway was associated with decreased early mortality , but had no effect on late mortality . A low lymphocyte count and a high serum potassium level were associated with early but not with late mortality . The type of antibiotic therapy had an effect on late but not on early mortality . Conclusions : Functional status at the time of hospital admission is a powerful predictor of mortality and should be incorporated into any scores or models that are used to predict mortality . While there are some common predictors of early and late in-hospital mortality , early mortality is not affected by the timing or type of antibiotic therapy , whereas late mortality is influenced by the type of antibiotic therapy . Hyperkalemia and lymphopenia are associated with early mortality . Abbreviations : CAP ϭ community-acquired pneumonia ; CI ϭ confidence interval ; FSA ϭ forward sortation area ; HRCT ϭ high-resolution CT ; OR ϭ odds ratio C ommunity-acquired pneumonia ( CAP ) is a common illness with an incidence rate of approximately 11.6 / 1,000 adults per year , 1 of which approx -\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"To determine the factors that predict in-hospital mortality among patients who require hospitalization for the treatment of community-acquired pneumonia ( CAP ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Study design : Prospective observational study of all patients who were admitted to six hospitals in Edmonton ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"AL , Canada , with a diagnosis of CAP from November 15 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"2000 , to November 14 , 2002 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Pneumonia was defined as two or more respiratory symptoms and signs and an opacity on a chest radiograph as interpreted by the attending physician .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Results : A total of 3,043 patients were enrolled in the study ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"246 of whom died ( 8.1 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"On multivariate analysis , increasing pneumonia severity score ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"increasing age , site of care ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"consultation with a respirologist or infectious diseases physician ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"and functional status at the time of admission were all independently predictive of mortality .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Increasing pneumonia severity risk score ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"increasing age , site of hospitalization ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"functional status , and consultation with an infectious diseases physician or a respirologist were independently associated with both early ( < 5 days ) and late ( > 5 days ) mortality .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"In contrast , partial or complete use of the pneumonia pathway was associated with decreased early mortality ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"but had no effect on late mortality .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"A low lymphocyte count and a high serum potassium level were associated with early but not with late mortality .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"The type of antibiotic therapy had an effect on late but not on early mortality .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Conclusions : Functional status at the time of hospital admission is a powerful predictor of mortality and should be incorporated into any scores or models that are used to predict mortality .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"While there are some common predictors of early and late in-hospital mortality ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"early mortality is not affected by the timing or type of antibiotic therapy ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"whereas late mortality is influenced by the type of antibiotic therapy .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"Hyperkalemia and lymphopenia are associated with early mortality .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"Abbreviations : CAP ϭ community-acquired pneumonia ; CI ϭ confidence interval ; FSA ϭ forward sortation area ; HRCT ϭ high-resolution CT ; OR ϭ odds ratio C ommunity-acquired pneumonia ( CAP ) is a common illness with an incidence rate of approximately 11.6 / 1,000 adults per year , 1 of which approx -\", \"label\": \"finding\", \"decision_reference\": \"other.rule\", \"id\": 24}]}"}]}
{"paper_id": "faeb9fe9e13d4bb64069905a64c28e2e36adf6a9", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe 39-terminal domain of the most conserved ORF1b in three of the four families of the order Nidovirales ( except for the family Arteriviridae ) encodes a ( putative ) 29-O-methyltransferase ( 29-O-MTase ) , known as non structural protein ( nsp ) 16 in the family Coronaviridae and implicated in methylation of the 59 cap structure of nidoviral mRNAs . As with coronavirus transcripts , arterivirus mRNAs are assumed to possess a 59 cap although no candidate MTases have been identified thus far . To address this knowledge gap , we analysed the uncharacterized nsp12 of arteriviruses , which occupies the ORF1b position equivalent to that of the nidovirus 29-O-MTase ( coronavirus nsp16 ) . In our in-depth bioinformatics analysis of nsp12 , the protein was confirmed to be family specific whilst having diverged much further than other nidovirus ORF1b-encoded proteins , including those of the family Coronaviridae . Only one invariant and several partially conserved , predominantly aromatic residues were identified in nsp12 , which may adopt a structure with alternating a-helices and b-strands , an organization also found in known MTases . However , no statistically significant similarity was found between nsp12 and the twofold larger coronavirus nsp16 , nor could we detect MTase activity in biochemical assays using recombinant equine arteritis virus ( EAV ) nsp12 . Our further analysis established that this subunit is essential for replication of this prototypic arterivirus . Using reverse genetics , we assessed the impact of 25 substitutions at 14 positions , yielding virus phenotypes ranging from WT-like to non-viable . Notably , replacement of the invariant phenylalanine 109 with tyrosine was lethal . We concluded that nsp12 plays an essential role during EAV replication , possibly by acting as a co-factor for another enzyme .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The 39-terminal domain of the most conserved ORF1b in three of the four families of the order Nidovirales ( except for the family Arteriviridae ) encodes a ( putative ) 29-O-methyltransferase ( 29-O-MTase ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"known as non structural protein ( nsp ) 16 in the family Coronaviridae and implicated in methylation of the 59 cap structure of nidoviral mRNAs .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"As with coronavirus transcripts , arterivirus mRNAs are assumed to possess a 59 cap although no candidate MTases have been identified thus far .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"To address this knowledge gap ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"we analysed the uncharacterized nsp12 of arteriviruses ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"which occupies the ORF1b position equivalent to that of the nidovirus 29-O-MTase ( coronavirus nsp16 ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"In our in-depth bioinformatics analysis of nsp12 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"the protein was confirmed to be family specific whilst having diverged much further than other nidovirus ORF1b-encoded proteins ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"including those of the family Coronaviridae .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Only one invariant and several partially conserved ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"predominantly aromatic residues were identified in nsp12 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"which may adopt a structure with alternating a-helices and b-strands ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"an organization also found in known MTases .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"However , no statistically significant similarity was found between nsp12 and the twofold larger coronavirus nsp16 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"nor could we detect MTase activity in biochemical assays using recombinant equine arteritis virus ( EAV ) nsp12 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Our further analysis established that this subunit is essential for replication of this prototypic arterivirus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Using reverse genetics , we assessed the impact of 25 substitutions at 14 positions ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"yielding virus phenotypes ranging from WT-like to non-viable .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Notably , replacement of the invariant phenylalanine 109 with tyrosine was lethal .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"We concluded that nsp12 plays an essential role during EAV replication ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"possibly by acting as a co-factor for another enzyme .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}]}"}]}
{"paper_id": "a2fc621a71cddf750d46902684501f5f18eba3a0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMiddle East respiratory syndrome coronavirus ( MERS-CoV ) has caused fatal infections , some through hospital-acquired transmission , in affected regions since its emergence in 2012 . Although the virus is not pandemic among humans , it poses a great threat to public health due to its zoonotic origin . Thus , both preventative and therapeutic countermeasures are urgently needed . In this study , we discovered a panel of neutralizing monoclonal antibodies ( mAbs ) against MERS-CoV , which mapped to a wide range of regions on the spike ( S ) protein of the virus . In addition to mAbs with neutralizing epitopes located on the receptor-binding domain , one mAb , 5F9 , which binds to the N-terminal domain ( NTD ) of the MERS-CoV S1 subunit , showed efficient neutralizing activity against the wild-type MERS-CoV strain EMC/2012 , with a half maximal inhibitory concentration of 0.2 μg/mL . We concluded that a novel neutralizing epitope for MERS-CoV also resides on the NTD of the S protein , indicating that the NTD might be important during the viral infection process . Our findings have significant implications for further vaccine design and for the development of prophylactic and therapeutic monoclonal immunotherapies against MERS-CoV infection .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Middle East respiratory syndrome coronavirus ( MERS-CoV ) has caused fatal infections ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"some through hospital-acquired transmission , in affected regions since its emergence in 2012 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Although the virus is not pandemic among humans ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"it poses a great threat to public health due to its zoonotic origin .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Thus , both preventative and therapeutic countermeasures are urgently needed .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"In this study , we discovered a panel of neutralizing monoclonal antibodies ( mAbs ) against MERS-CoV ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"which mapped to a wide range of regions on the spike ( S ) protein of the virus .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"In addition to mAbs with neutralizing epitopes located on the receptor-binding domain ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"one mAb , 5F9 , which binds to the N-terminal domain ( NTD ) of the MERS-CoV S1 subunit ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"showed efficient neutralizing activity against the wild-type MERS-CoV strain EMC/2012 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"with a half maximal inhibitory concentration of 0.2 μg/mL .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"We concluded that a novel neutralizing epitope for MERS-CoV also resides on the NTD of the S protein ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"indicating that the NTD might be important during the viral infection process .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Our findings have significant implications for further vaccine design and for the development of prophylactic and therapeutic monoclonal immunotherapies against MERS-CoV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}]}"}]}
{"paper_id": "12f1cc78e99a0b82f3225d10abe9a5649f1b33fc", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nLittle is known about the prevalence of mucosal antibodies induced by infection with human coronaviruses ( HCoV ) , including HCoV-229E and - OC43 and recently described strains ( HCoV-NL63 and - HKU1 ) . By enzyme-linked immunosorbent assay , we measured anti-HCoV IgG antibodies in serum and IgA antibodies in nasal wash specimens collected at seven U.S. sites from 105 adults aged 50 years and older ( mean age , 67 9 years ) with chronic obstructive pulmonary disease . Most patients ( 95 ( 90 % ) ) had at least one more chronic disease . More patients had serum antibody to each HCoV strain ( 104 ( 99 % ) had antibody to HCoV-229E , 105 ( 100 % ) had antibody to HCoV-OC43 , 103 ( 98 % ) had antibody to HCoV-NL63 , and 96 ( 91 % ) had antibody to HCoV-HKU1 ) than had antibody to each HCoV strain in nasal wash specimens ( 12 ( 11 % ) had antibody to HCoV-229E , 22 ( 22 % ) had antibody to HCoV-OC43 , 8 ( 8 % ) had antibody to HCoV-NL63 , and 31 ( 31 % ) had antibody to HCoV-HKU1 ) , respectively ( P < 0.0001 ) . The proportions of subjects with IgA antibodies in nasal wash specimens and the geometric mean IgA antibody titers were statistically higher for HCoV-OC43 and - HKU1 than for HCoV-229E and - NL63 . A higher proportion of patients with heart disease than not had IgA antibodies to HCoV-NL63 ( 6 ( 16 % ) versus 2 ( 3 % ) ; P 0.014 ) . Correlations were highest for serum antibody titers between group I strains ( HCoV-229E and - NL63 ( r 0.443 ; P < 0.0001 ) ) and between group II strains ( HCoV-OC43 and - HKU1 ( r 0.603 ; P < 0.0001 ) ) and not statistically significant between HCoV-NL63 and - OC43 and between HCoV-NL63 and - HKU1 . Patients likely had experienced infections with more than one HCoV strain , and IgG antibodies to these HCoV strains in serum were more likely to be detected than IgA antibodies to these HCoV strains in nasal wash specimens .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Little is known about the prevalence of mucosal antibodies induced by infection with human coronaviruses ( HCoV ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"including HCoV-229E and - OC43 and recently described strains ( HCoV-NL63 and - HKU1 ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"By enzyme-linked immunosorbent assay , we measured anti-HCoV IgG antibodies in serum and IgA antibodies in nasal wash specimens collected at seven U.S. sites from 105 adults aged 50 years and older ( mean age , 67 9 years ) with chronic obstructive pulmonary disease .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Most patients ( 95 ( 90 % ) ) had at least one more chronic disease .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"More patients had serum antibody to each HCoV strain ( 104 ( 99 % ) had antibody to HCoV-229E ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"105 ( 100 % ) had antibody to HCoV-OC43 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"103 ( 98 % ) had antibody to HCoV-NL63 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"and 96 ( 91 % ) had antibody to HCoV-HKU1 ) than had antibody to each HCoV strain in nasal wash specimens ( 12 ( 11 % ) had antibody to HCoV-229E ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"22 ( 22 % ) had antibody to HCoV-OC43 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"8 ( 8 % ) had antibody to HCoV-NL63 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"and 31 ( 31 % )\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"had antibody to HCoV-HKU1 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"respectively ( P < 0.0001 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"The proportions of subjects with IgA antibodies in nasal wash specimens and the geometric mean IgA antibody titers were statistically higher for HCoV-OC43 and - HKU1 than for HCoV-229E and - NL63 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"A higher proportion of patients with heart disease than not had IgA antibodies to HCoV-NL63 ( 6 ( 16 % ) versus 2 ( 3 % ) ; P 0.014 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Correlations were highest for serum antibody titers between group I strains ( HCoV-229E and - NL63 ( r 0.443 ; P < 0.0001 ) ) and between group II strains ( HCoV-OC43 and - HKU1 ( r 0.603 ; P < 0.0001 ) ) and not statistically significant between HCoV-NL63 and - OC43 and between HCoV-NL63 and - HKU1 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Patients likely had experienced infections with more than one HCoV strain ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"and IgG antibodies to these HCoV strains in serum were more likely to be detected than IgA antibodies to these HCoV strains in nasal wash specimens .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "9d3a476c4b3e5a3d03456a53c8840ee8d117808c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAs the practice of intensive animal production increases , there is a need for affordable treatment technologies that can help manage the large amounts of manure generated . Our approach has been to develop an efficient liquid-solid separation module using polymer technology and integrate this separation module into systems of treatment technologies for both the separated liquid and solids . We describe the progress that has been made in management techniques and new technological alternatives for manure treatment and generation of value added by-products based on the SELCO-Ecopurin â separation technology and experiences during the last five years in 12 livestock farms in Spain , Italy and the USA . High recovery of solids ( > 90 % ) makes the use of advanced purification of the liquid a more economical alternative . The liquid can be further treated to reduce N and P and produce effluents virtually free of these nutrients . Production of methane and energy was affected by solids concentration ; the anaerobic process was optimised with polymer application rate of 120 ppm during separation and a solids content of 13 % .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"As the practice of intensive animal production increases ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"there is a need for affordable treatment technologies that can help manage the large amounts of manure generated .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Our approach has been to develop an efficient liquid-solid separation module using polymer technology and integrate this separation module into systems of treatment technologies for both the separated liquid and solids .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"We describe the progress that has been made in management techniques and new technological alternatives for manure treatment and generation of value added by-products based on the SELCO-Ecopurin â separation technology and experiences during the last five years in 12 livestock farms in Spain , Italy and the USA .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"High recovery of solids ( > 90 % ) makes the use of advanced purification of the liquid a more economical alternative .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"The liquid can be further treated to reduce N and P and produce effluents virtually free of these nutrients .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"Production of methane and energy was affected by solids concentration ; the anaerobic process was optimised with polymer application rate of 120 ppm during separation and a solids content of 13 % .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}]}"}]}
{"paper_id": "acc85b2df8e1029b8e01e749a99ae706a7e5ff58", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe authors conducted a study using surveillance monitoring methodology to identify operatory contamination and to evaluate the effectiveness of infection control procedures . Viridans streptococci were evaluated as biological indicators of oral contamination . Viridans streptococci , abundant in human saliva , were detected on operatory surfaces after dental treatments were finished and surfaces were disinfected . The findings validate current concepts of infection control as demonstrated in barrier methods .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The authors conducted a study using surveillance monitoring methodology to identify operatory contamination and to evaluate the effectiveness of infection control procedures .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Viridans streptococci were evaluated as biological indicators of oral contamination .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"Viridans streptococci , abundant in human saliva ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 3}, {\"segment_text\": \"were detected on operatory surfaces after dental treatments were finished and surfaces were disinfected .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"The findings validate current concepts of infection control as demonstrated in barrier methods .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}]}"}]}
{"paper_id": "ca5bca39d98242b83a33252236335a766f0bb4bc", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAbbreviations : SARS , severe acute respiratory syndrome ; CoV , coronavirus ; PLpro , papain-like proteinase 2 ; 3CLpro , 3-chymotrypsinlike protease ; DUB , deubiquitination enzyme ; AMC , 7-amino-4-methylcoumarin ; FRET , fluorescence resonance energy transfer ; 6MP , 6mercaptopurine ; 6TG , 6-thioguanine . a v a i l a b l e a t w w w . s c i e n c e d i r e c t . c o m j o u r n a l h o m e p a g e : w w w . e l s e v i e r . c o m / l o c a t e / b i o c h e m p h a r m 0006-2952 / $ - see front matter #\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Abbreviations : SARS , severe acute respiratory syndrome ; CoV ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"coronavirus ; PLpro , papain-like proteinase 2 ; 3CLpro ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"3-chymotrypsinlike protease ; DUB , deubiquitination enzyme ; AMC ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"7-amino-4-methylcoumarin ; FRET , fluorescence resonance energy transfer ; 6MP ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 4}, {\"segment_text\": \"6mercaptopurine ; 6TG , 6-thioguanine .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 5}, {\"segment_text\": \"a v a i l a b l e a t w w w .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 6}, {\"segment_text\": \"s c i e n c e d i r e c t .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 7}, {\"segment_text\": \"c o m j o u r n a l h o m e p a g e : w w w .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 8}, {\"segment_text\": \"e l s e v i e r .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 9}, {\"segment_text\": \"c o m / l o c a t e / b i o c h e m p h a r m 0006-2952 / $ - see front matter #\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 10}]}"}]}
{"paper_id": "094439867383c6b40f9e81e1b67e6524da5dadab", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPrevious estimates of a generic level phylogeny for the ubiquitous parasitoid wasp subfamily Microgastrinae ( Hymenoptera ) have been problematic due to short internal branches deep in the phylogeny . These short branches might be attributed to a rapid radiation among the taxa , the use of genes that are unsuitable for the levels of divergence being examined , or insuYcient quantity of data . We added over 1200 nucleotides from four nuclear genes to a dataset derived from three genes to produce a dataset of over 3000 nucleotides per taxon . While the number of well-supported short branches in the phylogeny increased , we still did not obtain strong bootstrap support for every node . Parametric and nonparametric bootstrap simulations projected that an enormous , and likely unobtainable , amount of data would be required to get bootstrap support greater than 50 % for every node . However , a marked increase in the number of well-supported nodes was seen when we conducted a Bayesian analysis of a combined dataset generated from morphological characters added to the seven gene dataset . Our results suggest that , in some cases , combining morphological and genetic characters may be the most practical way to increase support for short branches deep in a phylogeny .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Previous estimates of a generic level phylogeny for the ubiquitous parasitoid wasp subfamily Microgastrinae ( Hymenoptera ) have been problematic due to short internal branches deep in the phylogeny .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"These short branches might be attributed to a rapid radiation among the taxa ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"the use of genes that are unsuitable for the levels of divergence being examined ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"or insuYcient quantity of data .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"We added over 1200 nucleotides from four nuclear genes to a dataset derived from three genes to produce a dataset of over 3000 nucleotides per taxon .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"While the number of well-supported short branches in the phylogeny increased ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"we still did not obtain strong bootstrap support for every node .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Parametric and nonparametric bootstrap simulations projected that an enormous ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and likely unobtainable , amount of data would be required to get bootstrap support greater than 50 % for every node .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"However , a marked increase in the number of well-supported nodes was seen when we conducted a Bayesian analysis of a combined dataset generated from morphological characters added to the seven gene dataset .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Our results suggest that , in some cases ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"combining morphological and genetic characters may be the most practical way to increase support for short branches deep in a phylogeny .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "f5e763d2253a378b85985424e5c3e3bc09d35583", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nConjugated polyelectrolytes ( CPEs ) have been widely used as reporters in colorimetric assays targeting nucleic acids . CPEs provide naked eye detection possibility by their superior optical properties however , as concentration of target analytes decrease , trace amounts of nucleic acid typically yield colorimetric responses that are not readily perceivable by naked eye . Herein , we report a pixelated analysis approach for correlating colorimetric responses of CPE with nucleic acid concentrations down to 1 nM , in plasma samples , utilizing a smart phone with an algorithm that can perform analytical testing and data processing . The detection strategy employed relies on conformational transitions between single stranded nucleic acid-cationic CPE duplexes and double stranded nucleic acid-CPE triplexes that yield distinct colorimetric responses for enabling naked eye detection of nucleic acids . Cationic poly ( N,N,N-triethyl-3 - ( ( 4-methylthiophen-3-yl ) oxy ) propan-1-aminium bromide ) is utilized as the CPE reporter deposited on a polyvinylidene fluoride ( PVDF ) membrane for nucleic acid assay . A smart phone application is developed to capture and digitize the colorimetric response of the individual pixels of the digital images of CPE on the PVDF membrane , followed by an analysis using the algorithm . The proposed pixelated approach enables precise quantification of nucleic acid assay concentrations , thereby eliminating the margin of error involved in conventional methodologies adopted for interpretation of colorimetric responses , for instance , RGB analysis . The obtained results illustrate that a ubiquitous smart phone could be utilized for point of care colorimetric nucleic acids assays in complex matrices without requiring sophisticated software or instrumentation .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Conjugated polyelectrolytes ( CPEs ) have been widely used as reporters in colorimetric assays targeting nucleic acids .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"CPEs provide naked eye detection possibility by their superior optical properties however ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"as concentration of target analytes decrease ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"trace amounts of nucleic acid typically yield colorimetric responses that are not readily perceivable by naked eye .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Herein , we report a pixelated analysis approach for correlating colorimetric responses of CPE with nucleic acid concentrations down to 1 nM ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"in plasma samples , utilizing a smart phone with an algorithm that can perform analytical testing and data processing .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"The detection strategy employed relies on conformational transitions between single stranded nucleic acid-cationic CPE duplexes and double stranded nucleic acid-CPE triplexes that yield distinct colorimetric responses for enabling naked eye detection of nucleic acids .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Cationic poly ( N,N,N-triethyl-3 - ( ( 4-methylthiophen-3-yl ) oxy ) propan-1-aminium bromide ) is utilized as the CPE reporter deposited on a polyvinylidene fluoride ( PVDF ) membrane for nucleic acid assay .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"A smart phone application is developed to capture and digitize the colorimetric response of the individual pixels of the digital images of CPE on the PVDF membrane ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"followed by an analysis using the algorithm .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"The proposed pixelated approach enables precise quantification of nucleic acid assay concentrations ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"thereby eliminating the margin of error involved in conventional methodologies adopted for interpretation of colorimetric responses ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"for instance , RGB analysis .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"The obtained results illustrate that a ubiquitous smart phone could be utilized for point of care colorimetric nucleic acids assays in complex matrices without requiring sophisticated software or instrumentation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "80a77923cc53e58abc35b1b8fcb56d6339055206", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\n19 Objectives : Development and validation of a single-step and accurate reverse transcriptase loop-20 mediated isothermal amplification technique ( RT-LAMP ) for rapid identification of SARS COV-2 21 relative to commercial quantitative reverse transcriptase real-time PCR ( qRT-PCR ) assays to allow 22 prompt initiation of proper medical care and containment of virus spread . 23 24 All rights reserved . No reuse allowed without permission . author/funder , who has granted medRxiv a license to display the preprint in perpetuity .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"19 Objectives : Development and validation of a single-step and accurate reverse transcriptase loop-20 mediated isothermal amplification technique ( RT-LAMP ) for rapid identification of SARS COV-2 21 relative to commercial quantitative reverse transcriptase real-time PCR ( qRT-PCR ) assays to allow 22 prompt initiation of proper medical care and containment of virus spread .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"23 24 All rights reserved .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 2}, {\"segment_text\": \"No reuse allowed without permission .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 3}, {\"segment_text\": \"author/funder , who has granted medRxiv a license to display the preprint in perpetuity .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 4}]}"}]}
{"paper_id": "4589d4013cf69c396e0fdb67131022fc11119654", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIn early 2013 , a novel avian-origin influenza A ( H7N9 ) virus emerged in China , and has caused sporadic human infections . The incubation period is the delay from infection until onset of symptoms , and varies from person to person . Few previous studies have examined whether the duration of the incubation period correlates with subsequent disease severity . We analyzed data of period of exposure on 395 human cases of laboratory-confirmed influenza A ( H7N9 ) virus infection in China in a Bayesian framework using a Weibull distribution . We found a longer incubation period for the 173 fatal cases with a mean of 3.7 days ( 95 % credibility interval , CrI : 3.4-4.1 ) , compared to a mean of 3.3 days ( 95 % CrI : 2.9-3.6 ) for the 222 non-fatal cases , and the difference in means was marginally significant at 0.47 days ( 95 % CrI : -0.04 , 0.99 ) . There was a statistically significant correlation between a longer incubation period and an increased risk of death after adjustment for age , sex , geographical location and underlying medical conditions ( adjusted odds ratio 1.70 per day increase in incubation period ; 95 % credibility interval 1.47-1.97 ) . We found a significant association between a longer incubation period and a greater risk of death among human H7N9 cases . The underlying biological mechanisms leading to this association deserve further exploration .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"In early 2013 , a novel avian-origin influenza A ( H7N9 ) virus emerged in China ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"and has caused sporadic human infections .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The incubation period is the delay from infection until onset of symptoms ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"and varies from person to person .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Few previous studies have examined whether the duration of the incubation period correlates with subsequent disease severity .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"We analyzed data of period of exposure on 395 human cases of laboratory-confirmed influenza A ( H7N9 ) virus infection in China in a Bayesian framework using a Weibull distribution .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"We found a longer incubation period for the 173 fatal cases with a mean of 3.7 days ( 95 % credibility interval , CrI : 3.4-4.1 ) ,\", \"label\": \"method\", \"decision_reference\": \"boundary method_vs_finding\", \"id\": 7}, {\"segment_text\": \"compared to a mean of 3.3 days ( 95 % CrI : 2.9-3.6 ) for the 222 non-fatal cases ,\", \"label\": \"method\", \"decision_reference\": \"boundary method_vs_finding\", \"id\": 8}, {\"segment_text\": \"and the difference in means was marginally significant at 0.47 days ( 95 % CrI : -0.04 , 0.99 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"There was a statistically significant correlation between a longer incubation period and an increased risk of death after adjustment for age ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"sex , geographical location and underlying medical conditions ( adjusted odds ratio 1.70 per day increase in incubation period ; 95 % credibility interval 1.47-1.97 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"We found a significant association between a longer incubation period and a greater risk of death among human H7N9 cases .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"The underlying biological mechanisms leading to this association deserve further exploration .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}]}"}]}
{"paper_id": "a95e414a7d1b5e0f079864da640729af20b318fe", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThis chapter reports the applicability of ionic liquids in the formation of different types of multicomponent reactions . Easy work-up , relatively short reaction times , good to high yields of the desired products , mild reaction conditions , low cost , availability , and reusability of the employed ionic liquids are the striking features of the reported methodologies .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"This chapter reports the applicability of ionic liquids in the formation of different types of multicomponent reactions .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Easy work-up , relatively short reaction times ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"good to high yields of the desired products ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"mild reaction conditions , low cost ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"availability , and reusability of the employed ionic liquids are the striking features of the reported methodologies .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}]}"}]}
{"paper_id": "eb979bab57933dd9c6c1c02684bd3d7002cb604c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nb r a z i l i a n j o u r n a l o f m i c r o b i o l o g y 4 9 ( 2 0 1 8 ) 790-794 h t t p : / / w w w . b j m i c r o b i o l . c o m . b r / Distemper Parvovirus Diarrhea Dog Co-infection a b s t r a c t Although the use of vaccines has controlled enteric diseases in dogs in many developed countries , vaccine coverage is still under optimal situation in Brazil . There is a large population of nonimmunized dogs and few studies about the identification of the viruses associated with diarrhea . To address this situation , stool samples from 325 dogs were analyzed by polymerase chain reaction for the detection of common enteric viruses such as Canine adenovirus ( CAdV ) , Canine coronavirus ( CCoV ) , Canine distemper virus ( CDV ) , Canine rotavirus ( CRV ) and Carnivorous protoparvovirus 1 ( canine parvovirus 2 ; CPV-2 ) . At least one of these species was detected in 56.6 % ( 184/325 ) of the samples . The viruses detected most frequently in either diarrheic or nondiarrheic dog feces were CPV-2 ( 54.3 % of the positive samples ) , CDV ( 45.1 % ) and CCoV ( 30.4 % ) , followed by CRV ( 8.2 % ) and CAdV ( 4.9 % ) . Only one agent was detected in the majority of the positive samples ( 63 % ) , but co-infections were present in 37 % of the positive samples and mainly included CDV and CPV-2 . The data presented herein can improve the clinical knowledge in regions with low vaccine coverage and highlight the need to improve the methods used to control these infectious diseases in domestic dogs .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"b r a z i l i a n j o u r n a l o f m i c r o b i o l o g y 4 9 ( 2 0 1 8 ) 790-794 h t t p : / / w w w .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 1}, {\"segment_text\": \"b j m i c r o b i o l .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 2}, {\"segment_text\": \"c o m .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 3}, {\"segment_text\": \"b r / Distemper Parvovirus Diarrhea Dog Co-infection a b s t r a c t Although the use of vaccines has controlled enteric diseases in dogs in many developed countries ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"vaccine coverage is still under optimal situation in Brazil .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"There is a large population of nonimmunized dogs and few studies about the identification of the viruses associated with diarrhea .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"To address this situation , stool samples from 325 dogs were analyzed by polymerase chain reaction for the detection of common enteric viruses such as Canine adenovirus ( CAdV ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Canine coronavirus ( CCoV ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Canine distemper virus ( CDV ) , Canine rotavirus ( CRV )\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"and Carnivorous protoparvovirus 1 ( canine parvovirus 2 ; CPV-2 ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"At least one of these species was detected in 56.6 % ( 184/325 ) of the samples .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"The viruses detected most frequently in either diarrheic or nondiarrheic dog feces were CPV-2 ( 54.3 % of the positive samples ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"CDV ( 45.1 % ) and CCoV ( 30.4 % ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"followed by CRV ( 8.2 % ) and CAdV ( 4.9 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Only one agent was detected in the majority of the positive samples ( 63 % ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"but co-infections were present in 37 % of the positive samples and mainly included CDV and CPV-2 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"The data presented herein can improve the clinical knowledge in regions with low vaccine coverage and highlight the need to improve the methods used to control these infectious diseases in domestic dogs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "997b681276cfd135c552fbbf4a3a5fe68b2c8a58", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSARS-CoV , as the pathogeny of severe acute respiratory syndrome ( SARS ) , is a mystery that the origin of the virus is still unknown even a few isolates ofthe virus were completely sequenced . To explore the genesis of SARS-ON , the FDOD method previously developed by us was applied to comparing complete genomes from 12 SARS-CoV isolates to those from 12 previously identified coronaviruses and an unrooted phylogenetic tree was constructed . Our results show that all SARS-CoV isolates were clustered into a clique and previously identified coronaviruses formed the other clique . Meanwhile , the three groups of coronaviruses depart from each other clearly in our tree that is consistent with the results of prevenient papers . Differently , from the topology of the phylogenetic tree we found that SARS-CoV is more close to group 1 within genus coronavirus . The topology map also shows that the 12 SARS-CoV isolates may be divided into two groups determined by the association with the SARS-CoV from the Hotel M in Hong Kong that may give some information about the infectious relationship of the SARS .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"SARS-CoV , as the pathogeny of severe acute respiratory syndrome ( SARS ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"is a mystery that the origin of the virus is still unknown even a few isolates ofthe virus were completely sequenced .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"To explore the genesis of SARS-ON ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"the FDOD method previously developed by us was applied to comparing complete genomes from 12 SARS-CoV isolates to those from 12 previously identified coronaviruses and an unrooted phylogenetic tree was constructed .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Our results show that all SARS-CoV isolates were clustered into a clique and previously identified coronaviruses formed the other clique .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Meanwhile , the three groups of coronaviruses depart from each other clearly in our tree that is consistent with the results of prevenient papers .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"Differently , from the topology of the phylogenetic tree we found that SARS-CoV is more close to group 1 within genus coronavirus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"The topology map also shows that the 12 SARS-CoV isolates may be divided into two groups determined by the association with the SARS-CoV from the Hotel M in Hong Kong that may give some information about the infectious relationship of the SARS .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}]}"}]}
{"paper_id": "eded781036843234ba2021a694474d2ee8f54d77", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nInfection with coronavirus results in the accumulation of genomic-sized mRNA and six to eight subgenomic mRNAs that make up a 3Ј coterminal nested-set structure . Genome-length negative-strand RNA and subgenomic-length negative-strand RNAs , each of which corresponds to each of the subgenomic mRNAs , also accumulate in infected cells . The present study examined whether the genome-length negative-strand RNA serves as a template for subgenomic mRNA synthesis . Genomelength replicative intermediate ( RI ) RNA was purified by two-dimensional gel electrophoresis of intracellular RNAs from cells infected with mouse hepatitis virus . RNase A treatment of the purified genome-length RI resulted in the production of the genome-length replicative form RNA , indicating that the genome-length RI included genome-length template RNA . RNase protection assays using the purified genome-length RI and two probes , which corresponded to the 5Ј 300-nt region of mRNA 6 and to the same region of mRNA 7 , showed the presence of nascent leader sequence-containing subgenomic mRNAs in the genome-length RI . These data demonstrated that the genome-length negative-strand RNA serves as a template for subgenomic mRNA synthesis .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Infection with coronavirus results in the accumulation of genomic-sized mRNA and six to eight subgenomic mRNAs that make up a 3Ј coterminal nested-set structure .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Genome-length negative-strand RNA and subgenomic-length negative-strand RNAs ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"each of which corresponds to each of the subgenomic mRNAs ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"also accumulate in infected cells .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"The present study examined whether the genome-length negative-strand RNA serves as a template for subgenomic mRNA synthesis .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Genomelength replicative intermediate ( RI ) RNA was purified by two-dimensional gel electrophoresis of intracellular RNAs from cells infected with mouse hepatitis virus .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"RNase A treatment of the purified genome-length RI resulted in the production of the genome-length replicative form RNA ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"indicating that the genome-length RI included genome-length template RNA .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"RNase protection assays using the purified genome-length RI and two probes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"which corresponded to the 5Ј 300-nt region of mRNA 6 and to the same region of mRNA 7 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"showed the presence of nascent leader sequence-containing subgenomic mRNAs in the genome-length RI .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"These data demonstrated that the genome-length negative-strand RNA serves as a template for subgenomic mRNA synthesis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "13710e1414a3d7090ceddc4354f8edfd7615245e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIn the last 20 years , surface plasmon resonance ( SPR ) and its advancement with imaging ( SPRi ) emerged as a suitable and reliable platform in clinical analysis for labelfree , sensitive , and real-time monitoring of biomolecular interactions . Thus , we report in this review the state of the art of clinical target detection with SPR-based biosensors in complex matrices ( e.g. , serum , saliva , blood , and urine ) as well as in standard solution when innovative approaches or advanced instrumentations were employed for improved detection . The principles of SPR-based biosensors are summarized first , focusing on the physical properties of the transducer , on the assays design , on the immobilization chemistry , and on new trends for implementing system analytical performances ( e.g. , coupling with nanoparticles ( NPs ) . Then we critically review the detection of analytes of interest in molecular diagnostics , such as hormones ( relevant also for anti-doping control ) and biomarkers of interest in inflammatory , cancer , and heart failure diseases . Antibody detection is reported in relation to immune disorder diagnostics . Subsequently , nucleic acid targets are considered for revealing genetic diseases ( e.g. , point mutation and single nucleotides polymorphism , SNPs ) as well as new emerging clinical markers ( microRNA ) and for pathogen detection . Finally , examples of pathogen detection by immunosensing were also analyzed . A parallel comparison with the reference methods was duly made , indicating the progress brought about by SPR technologies in clinical routine analysis .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"In the last 20 years ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"surface plasmon resonance ( SPR ) and its advancement with imaging ( SPRi ) emerged as a suitable and reliable platform in clinical analysis for labelfree ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"sensitive , and real-time monitoring of biomolecular interactions .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Thus , we report in this review the state of the art of clinical target detection with SPR-based biosensors in complex matrices ( e.g. , serum , saliva , blood , and urine ) as well as in standard solution when innovative approaches or advanced instrumentations were employed for improved detection .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"The principles of SPR-based biosensors are summarized first ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"focusing on the physical properties of the transducer ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"on the assays design , on the immobilization chemistry ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"and on new trends for implementing system analytical performances ( e.g. , coupling with nanoparticles ( NPs ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Then we critically review the detection of analytes of interest in molecular diagnostics ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"such as hormones ( relevant also for anti-doping control ) and biomarkers of interest in inflammatory ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"cancer , and heart failure diseases .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Antibody detection is reported in relation to immune disorder diagnostics .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"Subsequently , nucleic acid targets are considered for revealing genetic diseases ( e.g. , point mutation and single nucleotides polymorphism , SNPs ) as well as new emerging clinical markers ( microRNA ) and for pathogen detection .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"Finally , examples of pathogen detection by immunosensing were also analyzed .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"A parallel comparison with the reference methods was duly made ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"indicating the progress brought about by SPR technologies in clinical routine analysis .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}]}"}]}
{"paper_id": "81fa220064229342b7c1c65ccc6cf0cc60722248", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\n• Effect of time delay on pattern dynamics of an epidemic model is investigated . • Exact turing space is obtained by linear stability analysis . • Delay can change the pattern essence , such as the arm length and the direction of the stripe . • Time delay can largely postpone the pattern formation . • Time delay can widen the turing space . a b s t r a c t Time delay , accounting for constant incubation period or sojourn times in an infective state , widely exists in most biological systems like epidemiological models . However , the effect of time delay on spatial epidemic models is not well understood . In this paper , spatial pattern of an epidemic model with both nonlinear incidence rate and time delay is investigated . In particular , we mainly focus on the effect of time delay on the formation of spatial pattern . Through mathematical analysis , we gain the conditions for Hopf bifurcation and Turing bifurcation , and find exact Turing space in parameter space . Furthermore , numerical results show that time delay has a significant effect on pattern formation . The simulation results may enrich the finding of patterns and may well capture some key features in the epidemic models .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"• Effect of time delay on pattern dynamics of an epidemic model is investigated .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"• Exact turing space is obtained by linear stability analysis .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"• Delay can change the pattern essence ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"such as the arm length and the direction of the stripe .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"• Time delay can largely postpone the pattern formation .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"• Time delay can widen the turing space .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"a b s t r a c t Time delay ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"accounting for constant incubation period or sojourn times in an infective state ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"widely exists in most biological systems like epidemiological models .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"However , the effect of time delay on spatial epidemic models is not well understood .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"In this paper , spatial pattern of an epidemic model with both nonlinear incidence rate and time delay is investigated .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 11}, {\"segment_text\": \"In particular , we mainly focus on the effect of time delay on the formation of spatial pattern .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Through mathematical analysis , we gain the conditions for Hopf bifurcation and Turing bifurcation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"and find exact Turing space in parameter space .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Furthermore , numerical results show that time delay has a significant effect on pattern formation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"The simulation results may enrich the finding of patterns and may well capture some key features in the epidemic models .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "ed1be8e58bb5910ac90924e9812f4e164e45f3a1", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nDuck Tembusu virus ( DTMUV ) is a newly emerging pathogenic flavivirus that has caused massive economic losses to the duck industry in China . In the current study , a virulent strain of DTMUV , designated Du/CH/LSD / 110128 , was isolated from the livers of diseased ducks and attenuated by serial passage in embryonated chicken eggs . The virus was partially attenuated after 50 and 70 passages and was fully attenuated after 90 passages , based on mortality and morbidity rates and viral loads in inoculated ducklings . Fourteen amino acid substitutions were observed in the capsid , prM , envelope , NS1 , NS3 , NS4A , NS4B , and NS5 proteins of the fully attenuated strain of Du/CH/LSD / 110128 , which might be responsible for the observed changes in replication and pathogenicity . A 72-nucleotide deletion was also observed in the 3 = untranslated region of the virus after 30 passages . The fully attenuated virus retained the immunogenicity of the parental strain , providing effective protection to challenge with virulent Du/CH/LSD / 110128 , and may represent a suitable candidate as a vaccine strain against DTMUV infection in ducks . Our results also lay the foundation for future studies on the replication and pathogenic mechanisms of DTMUV .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Duck Tembusu virus ( DTMUV ) is a newly emerging pathogenic flavivirus that has caused massive economic losses to the duck industry in China .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"In the current study , a virulent strain of DTMUV ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"designated Du/CH/LSD / 110128 , was isolated from the livers of diseased ducks and attenuated by serial passage in embryonated chicken eggs .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"The virus was partially attenuated after 50 and 70 passages and was fully attenuated after 90 passages ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"based on mortality and morbidity rates and viral loads in inoculated ducklings .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Fourteen amino acid substitutions were observed in the capsid ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"prM , envelope , NS1 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"NS3 , NS4A , NS4B ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and NS5 proteins of the fully attenuated strain of Du/CH/LSD / 110128 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"which might be responsible for the observed changes in replication and pathogenicity .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"A 72-nucleotide deletion was also observed in the 3 = untranslated region of the virus after 30 passages .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"The fully attenuated virus retained the immunogenicity of the parental strain ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"providing effective protection to challenge with virulent Du/CH/LSD / 110128 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"and may represent a suitable candidate as a vaccine strain against DTMUV infection in ducks .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Our results also lay the foundation for future studies on the replication and pathogenic mechanisms of DTMUV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}]}"}]}
{"paper_id": "344057fa7bef9619bf39e1d681ab054048949e75", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nOBJECTIVES : Isolation due to the management of infectious diseases is thought to affect mental health , but the effects are still unknown . We examined the prevalence of anxiety symptoms and anger in persons isolated during the Middle East Respiratory Syndrome ( MERS ) epidemic both at isolation period and at four to six months after release from isolation . We also determined risk factors associated with these symptoms at four to six months . Of 1,692 who came in contact with MERS patients , 1,656 were not diagnosed with MERS . Among 1,656 , anxiety symptoms showed 7.6 % ( 95 % confidence interval ( CI ) , 6.3 to 8.9 % ) and feelings of anger were present in 16.6 % ( 95 % CI , 14.8 to 18.4 % ) during the isolation period . At four to six months after release from isolation , anxiety symptoms were observed in 3.0 % ( 95 % CI , 2.2 to 3.9 % ) . Feelings of anger were present in 6.4 % ( 95 % CI , 5.2 to 7.6 % ) . Risk factors for experiencing anxiety symptoms and anger at four to six months after release included symptoms related to MERS during isolation , inadequate supplies ( food , clothes , accommodation ) , social networking activities ( email , text , Internet ) , history of psychiatric illnesses , and financial loss . Mental health problems at four to six month after release from isolation might be prevented by providing mental health support to individuals with vulnerable mental health , and providing accurate information as well as appropriate supplies , including food , clothes , and accommodation .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"OBJECTIVES : Isolation due to the management of infectious diseases is thought to affect mental health ,\", \"label\": \"purpose\", \"decision_reference\": \"boundary background_vs_purpose\", \"id\": 1}, {\"segment_text\": \"but the effects are still unknown .\", \"label\": \"purpose\", \"decision_reference\": \"boundary background_vs_purpose\", \"id\": 2}, {\"segment_text\": \"We examined the prevalence of anxiety symptoms and anger in persons isolated during the Middle East Respiratory Syndrome ( MERS ) epidemic both at isolation period and at four to six months after release from isolation .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"We also determined risk factors associated with these symptoms at four to six months .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Of 1,692 who came in contact with MERS patients ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"1,656 were not diagnosed with MERS .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Among 1,656 , anxiety symptoms showed 7.6 % ( 95 % confidence interval ( CI ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"6.3 to 8.9 % ) and feelings of anger were present in 16.6 % ( 95 % CI , 14.8 to 18.4 % ) during the isolation period .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"At four to six months after release from isolation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"anxiety symptoms were observed in 3.0 % ( 95 % CI , 2.2 to 3.9 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"Feelings of anger were present in 6.4 % ( 95 % CI , 5.2 to 7.6 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"Risk factors for experiencing anxiety symptoms and anger at four to six months after release included symptoms related to MERS during isolation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"inadequate supplies ( food , clothes , accommodation ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"social networking activities ( email , text , Internet ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"history of psychiatric illnesses , and financial loss .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"Mental health problems at four to six month after release from isolation might be prevented by providing mental health support to individuals with vulnerable mental health ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"and providing accurate information as well as appropriate supplies ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"including food , clothes , and accommodation .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}]}"}]}
{"paper_id": "1a198805fc27ed8e271fa144181b5c2baac1559c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPhase I human clinical studies involving therapeutics for emerging and biodefense pathogens with low incidence , such as the severe acute respiratory syndrome coronavirus ( SARS-CoV ) , requires at a minimum preclinical evaluation of efficacy in two well-characterized and robust animal models . Thus , a ferret SARS-CoV model was evaluated over a period of 58 days following extensive optimization and characterization of the model in order to validate clinical , histopathological , virological and immunological endpoints . Ferrets that were infected intranasally with 10 3 TCID 50 SARS-CoV showed higher body temperature ( 2-6 d.p.i. ) , sneezing ( 5-10 d.p.i. ) , lesions ( 5-7 d.p.i. ) and decreased WBC/lymphocytes ( 2-5 d.p.i. ) . SARS-CoV was detected up to 7 d.p.i. in various tissues and excreta , while neutralizing antibody titers rose at 7 d.p.i. and peaked at 14 d.p.i. . At 29 d.p.i. , one group was challenged with 10 3 TCID 50 SARS-CoV , and an anamnestic response in neutralizing antibodies was evident with no detectable virus . This study supports the validity of the ferret model for use in evaluating efficacy of potential therapeutics to treat SARS .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Phase I human clinical studies involving therapeutics for emerging and biodefense pathogens with low incidence ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"such as the severe acute respiratory syndrome coronavirus ( SARS-CoV ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"requires at a minimum preclinical evaluation of efficacy in two well-characterized and robust animal models .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Thus , a ferret SARS-CoV model was evaluated over a period of 58 days following extensive optimization and characterization of the model in order to validate clinical ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"histopathological , virological and immunological endpoints .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Ferrets that were infected intranasally with 10 3 TCID 50 SARS-CoV showed higher body temperature ( 2-6 d.p.i. ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"sneezing ( 5-10 d.p.i. ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"lesions ( 5-7 d.p.i. ) and decreased WBC/lymphocytes ( 2-5 d.p.i. ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"SARS-CoV was detected up to 7 d.p.i. in various tissues and excreta ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"while neutralizing antibody titers rose at 7 d.p.i. and peaked at 14 d.p.i. .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"At 29 d.p.i. , one group was challenged with 10 3 TCID 50 SARS-CoV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and an anamnestic response in neutralizing antibodies was evident with no detectable virus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"This study supports the validity of the ferret model for use in evaluating efficacy of potential therapeutics to treat SARS .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "dbbf1b6713b9819bbe78a272e728951afa62ef95", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nInfectious disease nucleic acid amplification technologies ( NAAT ) have superior sensitivity , specificity , and rapid time to result compared to traditional microbiological methods . Recovery of concentrated , high quality pathogen nucleic acid ( NA ) from complex specimen matrices is required for optimal performance of several NA amplification/detection technologies such as polymerase chain reaction ( PCR ) . Fully integrated NAAT platforms that enable rapid sample-to-result workflows with minimal user input are generally restricted to larger reference lab settings , and their complexity and cost are prohibitive to widespread implementation in resource limited settings ( RLS ) . Identification of component technologies for incorporation of reliable and affordable sample preparation with pathogen NA amplification / detection into an integrated platform suitable for RLS , is a necessary first step toward achieving the overarching goal of reducing infectious disease-associated morbidity and mortality globally . In the current study , we evaluate the performance of six novel NA extraction technologies from different developers using blinded panels of stool , sputum and blood spiked with variable amounts of quality-controlled DNA-and/or RNA-based microbes . The extraction efficiencies were semi-quantitatively assessed using validated real-time reverse transcription ( RT ) - PCR assays specific for each microbe and comparing target-specific RT-PCR results to those obtained with reference NA extraction methods . The technologies were ranked based on overall diagnostic accuracy ( analytical sensitivity and specificity ) . Sample input and output volumes , total processing time , user-required manual steps and cost estimates were also examined for suitability in RLS . Together with the performance analysis , these metrics were used to select the more suitable candidate technologies for further optimization of integrated NA amplification and detection technologies for RLS .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Infectious disease nucleic acid amplification technologies ( NAAT ) have superior sensitivity ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"specificity , and rapid time to result compared to traditional microbiological methods .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Recovery of concentrated , high quality pathogen nucleic acid ( NA ) from complex specimen matrices is required for optimal performance of several NA amplification/detection technologies such as polymerase chain reaction ( PCR ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Fully integrated NAAT platforms that enable rapid sample-to-result workflows with minimal user input are generally restricted to larger reference lab settings ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"and their complexity and cost are prohibitive to widespread implementation in resource limited settings ( RLS ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Identification of component technologies for incorporation of reliable and affordable sample preparation with pathogen NA amplification / detection into an integrated platform suitable for RLS ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"is a necessary first step toward achieving the overarching goal of reducing infectious disease-associated morbidity and mortality globally .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"In the current study , we evaluate the performance of six novel NA extraction technologies from different developers using blinded panels of stool ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"sputum and blood spiked with variable amounts of quality-controlled DNA-and/or RNA-based microbes .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}, {\"segment_text\": \"The extraction efficiencies were semi-quantitatively assessed using validated real-time reverse transcription ( RT ) - PCR assays specific for each microbe and comparing target-specific RT-PCR results to those obtained with reference NA extraction methods .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"The technologies were ranked based on overall diagnostic accuracy ( analytical sensitivity and specificity ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Sample input and output volumes ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"total processing time , user-required manual steps and cost estimates were also examined for suitability in RLS .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"Together with the performance analysis ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"these metrics were used to select the more suitable candidate technologies for further optimization of integrated NA amplification and detection technologies for RLS .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 15}]}"}]}
{"paper_id": "80df1ce37238d763d313bcd0e673716c7c4458c1", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nWith respect to the asymptomatic transmission characteristics of the novel coronavirus that appeared in 2019 ( COVID-19 ) , a susceptible-asymptomatic-infected-recovered-death ( SAIRD ) model that considered human mobility was constructed in this study . The dissemination of COVID-19 was simulated using computational experiments to identify the mechanisms underlying the impact of city and residential lockdowns on controlling the spread of the epidemic . Results : The implementation of measures to lock down cities led to higher mortality rates in these cities , due to reduced mobility . Moreover , implementing city lockdown along with addition of hospital beds led to improved cure and reduced mortality rates . Stringent implementation and early lockdown of residential units effectively controlled the spread of the epidemic , and reduced the number of hospital bed requirements . Collectively , measures to lock down cities and residential units should be taken to prevent the spread of COVID-19 . In addition , medical resources should be increased in cities under lockdown . Implementation of these measures would reduce the spread of the virus to other cities and allow appropriate treatment of patients in cities under lockdown .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"With respect to the asymptomatic transmission characteristics of the novel coronavirus that appeared in 2019 ( COVID-19 ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"a susceptible-asymptomatic-infected-recovered-death ( SAIRD ) model that considered human mobility was constructed in this study .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"The dissemination of COVID-19 was simulated using computational experiments to identify the mechanisms underlying the impact of city and residential lockdowns on controlling the spread of the epidemic .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Results : The implementation of measures to lock down cities led to higher mortality rates in these cities , due to reduced mobility .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Moreover , implementing city lockdown along with addition of hospital beds led to improved cure and reduced mortality rates .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Stringent implementation and early lockdown of residential units effectively controlled the spread of the epidemic ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"and reduced the number of hospital bed requirements .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Collectively , measures to lock down cities and residential units should be taken to prevent the spread of COVID-19 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"In addition , medical resources should be increased in cities under lockdown .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Implementation of these measures would reduce the spread of the virus to other cities and allow appropriate treatment of patients in cities under lockdown .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "ef6d7a0388ffb5da9be98050ccc242315fac44a5", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nA novel reassortant avian influenza A virus ( H7N9 ) emerged in humans in Eastern China in late February 2013 . All virus strains were resistant to adamantanes ( amantadine and rimantadine ) , but susceptible to neuraminidase inhibitors ( NAIs ) ( oseltamivir and zanamivir ) . One strain ( A/shanghai/1 / 2013 ) contained the R294K substitution in the neuraminidase ( NA ) gene , indicating resistance to oseltamivir . Pyrosequencing has proven to be a useful tool in the surveillance of drug resistance in influenza A viruses . Here , we describe a reverse transcription ( RT ) - PCR assay coupled with pyrosequencing to identify the NA residues E120 , H276 , and R294 ( N9 numbering ) of H7N9 viruses . A total of 43 specimens ( 26 clinical samples and 17 isolates ) were tested . Only one isolate containing the E120V heterogenic mutation was detected by pyrosequencing and confirmed by Sanger sequencing . However , this mutation was not detected in the original clinical specimen . Since virus isolation might lead to the selection of variants that might not fully represent the virus population in the clinical specimens , we suggest that using pyrosequencing to detect NAI resistance in H7N9 viruses directly from clinical specimens rather than from cultured isolates . No cross-reactions with other types of influenza virus and respiratory tract viruses were found , and this assay has a sensitivity of 100 copies of synthetic RNA for all three codons . The high sensitivity and specificity of the assay should be sufficient for the detection of positive clinical specimens . In this study , we provide a rapid and reliable method for the characterization of NAI resistance in H7N9 viruses .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"A novel reassortant avian influenza A virus ( H7N9 ) emerged in humans in Eastern China in late February 2013 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"All virus strains were resistant to adamantanes ( amantadine and rimantadine ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"but susceptible to neuraminidase inhibitors ( NAIs ) ( oseltamivir and zanamivir ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"One strain ( A/shanghai/1 / 2013 ) contained the R294K substitution in the neuraminidase ( NA ) gene , indicating resistance to oseltamivir .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Pyrosequencing has proven to be a useful tool in the surveillance of drug resistance in influenza A viruses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Here , we describe a reverse transcription ( RT ) - PCR assay coupled with pyrosequencing to identify the NA residues E120 ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"H276 , and R294 ( N9 numbering ) of H7N9 viruses .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"A total of 43 specimens ( 26 clinical samples and 17 isolates ) were tested .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Only one isolate containing the E120V heterogenic mutation was detected by pyrosequencing and confirmed by Sanger sequencing .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"However , this mutation was not detected in the original clinical specimen .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Since virus isolation might lead to the selection of variants that might not fully represent the virus population in the clinical specimens ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"we suggest that using pyrosequencing to detect NAI resistance in H7N9 viruses directly from clinical specimens rather than from cultured isolates .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"No cross-reactions with other types of influenza virus and respiratory tract viruses were found ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"and this assay has a sensitivity of 100 copies of synthetic RNA for all three codons .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"The high sensitivity and specificity of the assay should be sufficient for the detection of positive clinical specimens .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"In this study , we provide a rapid and reliable method for the characterization of NAI resistance in H7N9 viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "aeb0c3a2994cf6075961a930c84245563aedea3e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThis is a preprint version , not peer-reviewed yet , and readers should treat it accordingly . 2 Summary Background : The COVID-19 disease has turned into a global pandemic with unprecedented challenges for the global community . Understanding the state of the disease and planning for future trajectories relies heavily on data on the spread and mortality . Yet official data coming from various countries are highly unreliable : symptoms similar to common cold in majority of cases and limited screening resources and delayed testing procedures may contribute to underestimation of the burden of disease . Anecdotal and more limited data are available , but few have systematically combined those with official statistics into a coherent view of the epidemic . This study is a modeling-in-real-time of the emerging outbreak for understanding the state of the disease . Our focus is on the case of the spread of disease in Iran , as one of the epicenters of the disease in the first months of 2020 . We develop a simple dynamic model of the epidemic to provide a more reliable picture of the state of the disease based on existing data . Building on the generic SEIR ( Susceptible , Exposed , Infected , and Recovered ) framework we incorporate two behavioral and logistical considerations . First we capture the endogenous changes in contact rate ( average contact per person ) as more death are reported . As a result the reproduction number changes endogenously in the model . Second we differentiate reported and true cases by including simple formulations for how only a fraction of cases might be diagnosed , and how that fraction changes in response to epidemic 's progression . In estimating the model we use both the official data as well as the discovered infected travelers and unofficial medical community estimates and triangulate these sources to build a more complete picture . Calibration is completed by forming a likelihood function for observing the actual time series data conditional on model parameters , and conducting a Markov Chain Monte Carlo simulations . The model is used to estimate current `` true '' cases of infection and death . We analyze the future trajectory of the disease under six conditions related to the seasonal effects and policy measures targeting social distancing . The model closely replicates the past data but also shows the true number of cases is likely far larger . We estimate about 493,000 current infected cases ( 90 % CI : 271K-810K ) as 1 A Persian summary of the article is provided as an appendix . است موجود انتها ضمیمه در فارسی به مقاله خالصه\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"This is a preprint version ,\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 1}, {\"segment_text\": \"not peer-reviewed yet , and readers should treat it accordingly .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 2}, {\"segment_text\": \"2 Summary Background : The COVID-19 disease has turned into a global pandemic with unprecedented challenges for the global community .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Understanding the state of the disease and planning for future trajectories relies heavily on data on the spread and mortality .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Yet official data coming from various countries are highly unreliable : symptoms similar to common cold in majority of cases and limited screening resources and delayed testing procedures may contribute to underestimation of the burden of disease .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Anecdotal and more limited data are available ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"but few have systematically combined those with official statistics into a coherent view of the epidemic .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"This study is a modeling-in-real-time of the emerging outbreak for understanding the state of the disease .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"Our focus is on the case of the spread of disease in Iran ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}, {\"segment_text\": \"as one of the epicenters of the disease in the first months of 2020 .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 10}, {\"segment_text\": \"We develop a simple dynamic model of the epidemic to provide a more reliable picture of the state of the disease based on existing data .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Building on the generic SEIR ( Susceptible , Exposed , Infected , and Recovered ) framework we incorporate two behavioral and logistical considerations .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"First we capture the endogenous changes in contact rate ( average contact per person ) as more death are reported .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"As a result the reproduction number changes endogenously in the model .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"Second we differentiate reported and true cases by including simple formulations for how only a fraction of cases might be diagnosed ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 15}, {\"segment_text\": \"and how that fraction changes in response to epidemic 's progression .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 16}, {\"segment_text\": \"In estimating the model we use both the official data as well as the discovered infected travelers and unofficial medical community estimates and triangulate these sources to build a more complete picture .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 17}, {\"segment_text\": \"Calibration is completed by forming a likelihood function for observing the actual time series data conditional on model parameters ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 18}, {\"segment_text\": \"and conducting a Markov Chain Monte Carlo simulations .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 19}, {\"segment_text\": \"The model is used to estimate current `` true '' cases of infection and death .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 20}, {\"segment_text\": \"We analyze the future trajectory of the disease under six conditions related to the seasonal effects and policy measures targeting social distancing .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 21}, {\"segment_text\": \"The model closely replicates the past data but also shows the true number of cases is likely far larger .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"We estimate about 493,000 current infected cases ( 90 % CI : 271K-810K ) as 1 A Persian summary of the article is provided as an appendix .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"است موجود انتها ضمیمه در فارسی به مقاله خالصه\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 24}]}"}]}
{"paper_id": "cb22558ac58c43426eebd6a86dd22201c1977005", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIn the control of infectious diseases , epidemiologic information and useful clustering algorithms can be integrated to garner key indicators from huge amounts of daily surveillance information for the need of early intervention . This chapter first introduces the temporal , spatial and spatiotemporal clustering algorithms commonly used in surveillance systems - the key concepts behind the algorithms and the criteria for appropriate use . This description is followed by an introduction to different statistical methods that can be used to analyze the clustering patterns which occur in different epidemics and epidemic stages . Research methods such as flexible analysis of irregular spatial and temporal clusters , adjustment of personal risk factors , and Bayesian approaches to disease mapping and better prediction all will be needed to understand the epidemiologic characteristics of infectious diseases in the future .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"In the control of infectious diseases ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"epidemiologic information and useful clustering algorithms can be integrated to garner key indicators from huge amounts of daily surveillance information for the need of early intervention .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"This chapter first introduces the temporal ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"spatial and spatiotemporal clustering algorithms commonly used in surveillance systems - the key concepts behind the algorithms and the criteria for appropriate use .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"This description is followed by an introduction to different statistical methods that can be used to analyze the clustering patterns which occur in different epidemics and epidemic stages .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Research methods such as flexible analysis of irregular spatial and temporal clusters ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"adjustment of personal risk factors ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"and Bayesian approaches to disease mapping and better prediction all will be needed to understand the epidemiologic characteristics of infectious diseases in the future .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}]}"}]}
{"paper_id": "e129d1575042d4451c2da24f2a9fedeaad356d0b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThis report explains the employing of a combination test of traditional cell culture with a quantitative real-time PCR for assessment of the antiviral effect of zinc sulfate ( ZnSO 4 ) on herpes simplex virus ( HSV ) - infected Vero cells . Our evidence showed that the treatment with 0.3 mM ZnSO 4 strongly inhibited the replication of virus progeny ( MOI 0.001 ) at least 68-fold less . On the other hand , the IC50 demonstrated that the highest activity of ZnSO 4 was at the 0.23 mM concentration .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"This report explains the employing of a combination test of traditional cell culture with a quantitative real-time PCR for assessment of the antiviral effect of zinc sulfate ( ZnSO 4 ) on herpes simplex virus ( HSV ) - infected Vero cells .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Our evidence showed that the treatment with 0.3 mM ZnSO 4 strongly inhibited the replication of virus progeny ( MOI 0.001 ) at least 68-fold less .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"On the other hand , the IC50 demonstrated that the highest activity of ZnSO 4 was at the 0.23 mM concentration .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 3}]}"}]}
{"paper_id": "31042ccf8374ad96d39d8156d9e2ced042734ba9", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Despite current knowledge of mutations in 45 genes that can cause nonsyndromic sensorineural hearing loss ( SNHL ) , no unified clinical test has been developed that can comprehensively detect mutations in multiple genes . We therefore designed Affymetrix resequencing microarrays capable of resequencing 13 genes mutated in SNHL ( GJB2 , GJB6 , CDH23 , KCNE1 , KCNQ1 , MYO7A , OTOF , PDS , MYO6 , SLC26A5 , TMIE , TMPRSS3 , USH1C ) . We present results from hearing loss arrays developed in two different research facilities and highlight some of the approaches we adopted to enhance the applicability of resequencing arrays in a clinical setting . Results : We leveraged sequence and intensity pattern features responsible for diminished coverage and accuracy and developed a novel algorithm , sPROFILER , which resolved > 80 % of no-calls from GSEQ and allowed 99.6 % ( range : 99.2-99.8 % ) of sequence to be called , while maintaining overall accuracy at > 99.8 % based upon dideoxy sequencing comparison . Conclusions : Together , these findings provide insight into critical issues for disease-centered resequencing protocols suitable for clinical application and support the use of array-based resequencing technology as a valuable molecular diagnostic tool for pediatric SNHL and other genetic diseases with substantial genetic heterogeneity .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Despite current knowledge of mutations in 45 genes that can cause nonsyndromic sensorineural hearing loss ( SNHL ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"no unified clinical test has been developed that can comprehensively detect mutations in multiple genes .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"We therefore designed Affymetrix resequencing microarrays capable of resequencing 13 genes mutated in SNHL ( GJB2 , GJB6 , CDH23 , KCNE1 , KCNQ1 , MYO7A , OTOF , PDS , MYO6 , SLC26A5 , TMIE , TMPRSS3 , USH1C ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"We present results from hearing loss arrays developed in two different research facilities and highlight some of the approaches we adopted to enhance the applicability of resequencing arrays in a clinical setting .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Results : We leveraged sequence and intensity pattern features responsible for diminished coverage and accuracy and developed a novel algorithm ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"sPROFILER , which resolved > 80 % of no-calls from GSEQ and allowed 99.6 % ( range : 99.2-99.8 % ) of sequence to be called ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"while maintaining overall accuracy at > 99.8 % based upon dideoxy sequencing comparison .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Conclusions : Together , these findings provide insight into critical issues for disease-centered resequencing protocols suitable for clinical application and support the use of array-based resequencing technology as a valuable molecular diagnostic tool for pediatric SNHL and other genetic diseases with substantial genetic heterogeneity .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}]}"}]}
{"paper_id": "dd2054667f5f1db92d4649fc420d0d86dc39dcd9", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe cellular actin cytoskeleton presents a barrier that must be overcome by many viruses , and it has become increasingly apparent many viral species have developed a diverse repertoire of mechanisms to hijack cellular actin-regulating signalling pathways as part of their cell entry processes . The Rho family GTPase Cdc42 is appreciated as a key moderator of cellular actin dynamics , and the development of specific Cdc42-inhibiting agents has given us an unprecedented ability to investigate its individual role in signalling pathways . However , investigative use of said agents , and the subsequent characterisation of the role Cdc42 plays in viral entry processes has been lacking . Here , we describe the current literature on the role of Cdc42 in human immunodeficiency virus ( HIV ) -1 cell entry , which represents the most investigated instance of Cdc42 function in viral cell entry processes , and also review evidence of Cdc42 use in other RNA virus cell entries , demonstrating prime areas for more extensive research using similar techniques .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The cellular actin cytoskeleton presents a barrier that must be overcome by many viruses ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"and it has become increasingly apparent many viral species have developed a diverse repertoire of mechanisms to hijack cellular actin-regulating signalling pathways as part of their cell entry processes .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The Rho family GTPase Cdc42 is appreciated as a key moderator of cellular actin dynamics ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"and the development of specific Cdc42-inhibiting agents has given us an unprecedented ability to investigate its individual role in signalling pathways .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"However , investigative use of said agents ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"and the subsequent characterisation of the role Cdc42 plays in viral entry processes has been lacking .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"Here , we describe the current literature on the role of Cdc42 in human immunodeficiency virus ( HIV ) -1 cell entry ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"which represents the most investigated instance of Cdc42 function in viral cell entry processes ,\", \"label\": \"purpose\", \"decision_reference\": \"boundary background_vs_purpose\", \"id\": 8}, {\"segment_text\": \"and also review evidence of Cdc42 use in other RNA virus cell entries ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}, {\"segment_text\": \"demonstrating prime areas for more extensive research using similar techniques .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 10}]}"}]}
{"paper_id": "06feefc13f34b0d6ca007bf080b5e4f42f11a692", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nNipah virus ( NiV ) and Hendra virus ( HeV ) are closely related , recently emerged paramyxoviruses that are capable of causing considerable morbidity and mortality in several mammalian species , including humans . Henipavirus-specific vaccines are still commercially unavailable , and development of novel antiviral strategies to prevent lethal infections due to henipaviruses is highly desirable . Here we describe the development of adeno-associated virus ( AAV ) vaccines expressing the NiV G protein . Characterization of these vaccines in mice demonstrated that a single intramuscular AAV injection was sufficient to induce a potent and longlasting antibody response . Translational studies in hamsters further demonstrated that all vaccinated animals were protected against lethal challenge with NiV . In addition , this vaccine induced a cross-protective immune response that was able to protect 50 % of the animals against a challenge by HeV . This study presents a new efficient vaccination strategy against henipaviruses and opens novel perspectives on the use of AAV vectors as vaccines against emergent diseases .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Nipah virus ( NiV ) and Hendra virus ( HeV ) are closely related ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"recently emerged paramyxoviruses that are capable of causing considerable morbidity and mortality in several mammalian species , including humans .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Henipavirus-specific vaccines are still commercially unavailable ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"and development of novel antiviral strategies to prevent lethal infections due to henipaviruses is highly desirable .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Here we describe the development of adeno-associated virus ( AAV ) vaccines expressing the NiV G protein .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Characterization of these vaccines in mice demonstrated that a single intramuscular AAV injection was sufficient to induce a potent and longlasting antibody response .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Translational studies in hamsters further demonstrated that all vaccinated animals were protected against lethal challenge with NiV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"In addition , this vaccine induced a cross-protective immune response that was able to protect 50 % of the animals against a challenge by HeV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"This study presents a new efficient vaccination strategy against henipaviruses and opens novel perspectives on the use of AAV vectors as vaccines against emergent diseases .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}]}"}]}
{"paper_id": "2ff4902f8704407bd2f72325ee5ea75908919a54", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nZika virus ( ZIKV ) remained largely quiescent for nearly six decades after its first appearance in 1947 . ZIKV reappeared after 2007 , resulting in a declaration of an international `` public health emergency '' in 2016 by the World Health Organization ( WHO ) . Until this time , ZIKV was considered to induce only mild illness , but it has now been established as the cause of severe clinical manifestations , including fetal anomalies , neurological problems , and autoimmune disorders . Infection during pregnancy can cause congenital brain abnormalities , including microcephaly and neurological degeneration , and in other cases , Guillain-Barré syndrome , making infections with ZIKV a substantial public health concern . Genomic and molecular investigations are underway to investigate ZIKV pathology and its recent enhanced pathogenicity , as well as to design safe and potent vaccines , drugs , and therapeutics . This review describes progress in the design and development of various anti-ZIKV therapeutics , including drugs targeting virus entry into cells and the helicase protein , nucleosides , inhibitors of NS3 protein , small molecules , methyltransferase inhibitors , interferons , repurposed drugs , drugs designed with the aid of computers , neutralizing antibodies , convalescent serum , antibodies that limit antibody-dependent enhancement , and herbal medicines . Additionally , covalent inhibitors of viral protein expression and anti-Toll-like receptor molecules are discussed . To counter ZIKVassociated disease , we need to make rapid progress in developing novel therapies that work effectually to inhibit ZIKV .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Zika virus ( ZIKV ) remained largely quiescent for nearly six decades after its first appearance in 1947 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"ZIKV reappeared after 2007 , resulting in a declaration of an international `` public health emergency '' in 2016 by the World Health Organization ( WHO ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Until this time , ZIKV was considered to induce only mild illness ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"but it has now been established as the cause of severe clinical manifestations ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"including fetal anomalies , neurological problems , and autoimmune disorders .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Infection during pregnancy can cause congenital brain abnormalities ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"including microcephaly and neurological degeneration ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"and in other cases , Guillain-Barré syndrome ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"making infections with ZIKV a substantial public health concern .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"Genomic and molecular investigations are underway to investigate ZIKV pathology and its recent enhanced pathogenicity ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"as well as to design safe and potent vaccines , drugs , and therapeutics .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"This review describes progress in the design and development of various anti-ZIKV therapeutics ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}, {\"segment_text\": \"including drugs targeting virus entry into cells and the helicase protein ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 13}, {\"segment_text\": \"nucleosides , inhibitors of NS3 protein ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 14}, {\"segment_text\": \"small molecules , methyltransferase inhibitors ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 15}, {\"segment_text\": \"interferons , repurposed drugs , drugs designed with the aid of computers ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 16}, {\"segment_text\": \"neutralizing antibodies , convalescent serum ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 17}, {\"segment_text\": \"antibodies that limit antibody-dependent enhancement , and herbal medicines .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 18}, {\"segment_text\": \"Additionally , covalent inhibitors of viral protein expression and anti-Toll-like receptor molecules are discussed .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 19}, {\"segment_text\": \"To counter ZIKVassociated disease , we need to make rapid progress in developing novel therapies that work effectually to inhibit ZIKV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}]}"}]}
{"paper_id": "08911cdc65e71e6398ca79b46806e6c8b2b730ae", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nmedRxiv preprint immunology 2015 ; 156 ( 1 ) : 19-27 . 15 . Gu J , Gong E , Zhang B , et al. . Multiple organ infection and the pathogenesis of SARS . J Exp Med 2005 ; 202 ( 3 ) : 415-24 . All rights reserved . No reuse allowed without permission . author/funder , who has granted medRxiv a license to display the preprint in perpetuity .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"medRxiv preprint immunology 2015 ; 156 ( 1 ) : 19-27 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 1}, {\"segment_text\": \"15 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 2}, {\"segment_text\": \"Gu J , Gong E ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 3}, {\"segment_text\": \"Zhang B , et al. .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 4}, {\"segment_text\": \"Multiple organ infection and the pathogenesis of SARS .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 5}, {\"segment_text\": \"J Exp Med 2005 ; 202 ( 3 ) : 415-24 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 6}, {\"segment_text\": \"All rights reserved .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 7}, {\"segment_text\": \"No reuse allowed without permission .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 8}, {\"segment_text\": \"author/funder , who has granted medRxiv a license to display the preprint in perpetuity .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 9}]}"}]}
{"paper_id": "1a8daad89d2701b4cf603e668f6aab1209b6237e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRationale : Emphysema and osteoporosis are epidemiologically associated diseases of cigarette smokers . The causal mechanism ( s ) linking these illnesses is unknown . We hypothesized autoimmune responses may be involved in both disorders . Objectives : To discover an antigen-specific autoimmune response associated with both emphysema and osteoporosis among smokers . Methods : Replicate nonbiased discovery assays indicated that autoimmunity to glucose regulated protein 78 ( GRP78 ) , an endoplasmic reticulum chaperone and cell surface signaling receptor , is present in many smokers . Subject assessments included spirometry , chest CT scans , dual x-ray absorptiometry , and immunoblots for anti-GRP78 IgG . Anti-GRP78 autoantibodies were isolated from patient plasma by affinity chromatography , leukocyte functions assessed by flow cytometry , and soluble metabolites and mediators measured by immunoassays . Measurements and Main Results : Circulating anti-GRP78 IgG autoantibodies were detected in plasma specimens from 86 ( 32 % ) of the 265 smoking subjects . Anti-GRP78 autoantibodies were singularly prevalent among subjects with radiographic emphysema ( OR 3.1 , 95 % CI 1.7-5.7 , p = 0.003 ) . Anti-GRP78 autoantibodies were also associated with osteoporosis ( OR 4.7 , 95 % CI 1.7-13.3 , p = 0.002 ) , and increased circulating bone metabolites ( p = 0.006 ) . Among emphysematous subjects , GRP78 protein was an autoantigen of CD4 T-cells , stimulating lymphocyte proliferation ( p = 0.0002 ) and IFN-gamma production ( p = 0.03 ) . Patient-derived anti-GRP78 autoantibodies had avidities for osteoclasts and macrophages , and increased macrophage NFkB phosphorylation ( p = 0.005 ) and productions of IL-8 , CCL-2 , and MMP9 ( p = 0.005 , 0.007 , 0.03 , respectively ) . Conclusions : Humoral and cellular GRP78 autoimmune responses in smokers have numerous biologically-relevant proinflammatory and other deleterious actions , and are associated with emphysema and osteoporosis . These findings may have relevance for the pathogenesis of smoking-associated diseases , and development of biomarker immunoassays and/or novel treatments for these disorders .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Rationale : Emphysema and osteoporosis are epidemiologically associated diseases of cigarette smokers .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The causal mechanism ( s ) linking these illnesses is unknown .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"We hypothesized autoimmune responses may be involved in both disorders .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Objectives : To discover an antigen-specific autoimmune response associated with both emphysema and osteoporosis among smokers .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Methods : Replicate nonbiased discovery assays indicated that autoimmunity to glucose regulated protein 78 ( GRP78 ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"an endoplasmic reticulum chaperone and cell surface signaling receptor ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"is present in many smokers .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Subject assessments included spirometry , chest CT scans ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"dual x-ray absorptiometry , and immunoblots for anti-GRP78 IgG .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Anti-GRP78 autoantibodies were isolated from patient plasma by affinity chromatography ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"leukocyte functions assessed by flow cytometry ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"and soluble metabolites and mediators measured by immunoassays .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"Measurements and Main Results : Circulating anti-GRP78 IgG autoantibodies were detected in plasma specimens from 86 ( 32 % ) of the 265 smoking subjects .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Anti-GRP78 autoantibodies were singularly prevalent among subjects with radiographic emphysema ( OR 3.1 , 95 % CI 1.7-5.7 , p = 0.003 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Anti-GRP78 autoantibodies were also associated with osteoporosis ( OR 4.7 , 95 % CI 1.7-13.3 , p = 0.002 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"and increased circulating bone metabolites ( p = 0.006 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Among emphysematous subjects , GRP78 protein was an autoantigen of CD4 T-cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"stimulating lymphocyte proliferation ( p = 0.0002 ) and IFN-gamma production ( p = 0.03 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Patient-derived anti-GRP78 autoantibodies had avidities for osteoclasts and macrophages ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"and increased macrophage NFkB phosphorylation ( p = 0.005 ) and productions of IL-8 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"CCL-2 , and MMP9 ( p = 0.005 , 0.007 , 0.03 , respectively ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"Conclusions : Humoral and cellular GRP78 autoimmune responses in smokers have numerous biologically-relevant proinflammatory and other deleterious actions ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"and are associated with emphysema and osteoporosis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"These findings may have relevance for the pathogenesis of smoking-associated diseases ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}, {\"segment_text\": \"and development of biomarker immunoassays and/or novel treatments for these disorders .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 25}]}"}]}
{"paper_id": "159542778cfb78258a07f195a5b4aaf400cdcbcb", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Many infectious diseases of public health importance display annual seasonal patterns in their incidence . We aimed to systematically document the seasonality of several human infectious disease pathogens in England and Wales , highlighting those organisms that appear weather-sensitive and therefore may be influenced by climate change in the future . Methods : Data on infections in England and Wales from 1989 to 2014 were extracted from the Public Health England ( PHE ) SGSS surveillance database . We conducted a weekly , monthly and quarterly time series analysis of 277 pathogen serotypes . Each organism 's time series was forecasted using the TBATS package in R , with seasonality detected using model fit statistics . Meteorological data hosted on the MEDMI Platform were extracted at a monthly resolution for 2001-2011 . The organisms were then clustered by K-means into two groups based on cross correlation coefficients with the weather variables . Results : Examination of 12.9 million infection episodes found seasonal components in 91/277 ( 33 % ) organism serotypes . Salmonella showed seasonal and non-seasonal serotypes . These results were visualised in an online Rshiny application . Seasonal organisms were then clustered into two groups based on their correlations with weather . Group 1 had positive correlations with temperature ( max , mean and min ) , sunshine and vapour pressure and inverse correlations with mean wind speed , relative humidity , ground frost and air frost . Group 2 had the opposite but also slight positive correlations with rainfall ( mm , > 1 mm , > 10 mm ) . The detection of seasonality in pathogen time series data and the identification of relevant weather predictors can improve forecasting and public health planning . Big data analytics and online visualisation allow the relationship between pathogen incidence and weather patterns to be clarified .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Many infectious diseases of public health importance display annual seasonal patterns in their incidence .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"We aimed to systematically document the seasonality of several human infectious disease pathogens in England and Wales ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"highlighting those organisms that appear weather-sensitive and therefore may be influenced by climate change in the future .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"Methods : Data on infections in England and Wales from 1989 to 2014 were extracted from the Public Health England ( PHE ) SGSS surveillance database .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"We conducted a weekly , monthly and quarterly time series analysis of 277 pathogen serotypes .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Each organism 's time series was forecasted using the TBATS package in R ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"with seasonality detected using model fit statistics .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Meteorological data hosted on the MEDMI Platform were extracted at a monthly resolution for 2001-2011 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The organisms were then clustered by K-means into two groups based on cross correlation coefficients with the weather variables .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Results : Examination of 12.9 million infection episodes found seasonal components in 91/277 ( 33 % ) organism serotypes .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Salmonella showed seasonal and non-seasonal serotypes .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"These results were visualised in an online Rshiny application .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Seasonal organisms were then clustered into two groups based on their correlations with weather .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Group 1 had positive correlations with temperature ( max , mean and min ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"sunshine and vapour pressure and inverse correlations with mean wind speed ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"relative humidity , ground frost and air frost .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Group 2 had the opposite but also slight positive correlations with rainfall ( mm , > 1 mm , > 10 mm ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"The detection of seasonality in pathogen time series data and the identification of relevant weather predictors can improve forecasting and public health planning .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Big data analytics and online visualisation allow the relationship between pathogen incidence and weather patterns to be clarified .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}]}"}]}
{"paper_id": "1d5d0d4183fe51d96f016b2ca4b995a8a5efcdf7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIn the last two decades , several high impact zoonotic disease outbreaks have been linked to bat-borne viruses . These include SARS coronavirus , Hendra virus and Nipah virus . In addition , it has been suspected that ebolaviruses and MERS coronavirus are also linked to bats . It is being increasingly accepted that bats are potential reservoirs of a large number of known and unknown viruses , many of which could spillover into animal and human populations . However , our knowledge into basic bat biology and immunology is very limited and we have little understanding of major factors contributing to the risk of bat virus spillover events . Here we provide a brief review of the latest findings in bat viruses and their potential risk of crossspecies transmission .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"In the last two decades ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"several high impact zoonotic disease outbreaks have been linked to bat-borne viruses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"These include SARS coronavirus , Hendra virus and Nipah virus .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"In addition , it has been suspected that ebolaviruses and MERS coronavirus are also linked to bats .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"It is being increasingly accepted that bats are potential reservoirs of a large number of known and unknown viruses ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"many of which could spillover into animal and human populations .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"However , our knowledge into basic bat biology and immunology is very limited and we have little understanding of major factors contributing to the risk of bat virus spillover events .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"Here we provide a brief review of the latest findings in bat viruses and their potential risk of crossspecies transmission .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}]}"}]}
{"paper_id": "a287ba01bfbdce5eaf1b6d8bc59bfe3eeac8bca9", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThis paper presents a label-free affinity-based capacitive biosensor using interdigitated electrodes . Using an optimized process of DNA probe preparation to minimize the effect of contaminants in commercial thiolated DNA probe , the electrode surface was functionalized with the 24-nucleotide DNA probes based on the West Nile virus sequence ( Kunjin strain ) . The biosensor has the ability to detect complementary DNA fragments with a detection limit down to 20 DNA target molecules ( 1.5 aM range ) , making it suitable for a practical point-of-care ( POC ) platform for low target count clinical applications without the need for amplification . The reproducibility of the biosensor detection was improved with efficient covalent immobilization of purified single-stranded DNA probe oligomers on cleaned gold microelectrodes . In addition to the low detection limit , the biosensor showed a dynamic range of detection from 1 mL À 1 to 10 5 mL À 1 target molecules ( 20 to 2 million targets ) , making it suitable for sample analysis in a typical clinical application environment . The binding results presented in this paper were validated using fluorescent oligomers .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"This paper presents a label-free affinity-based capacitive biosensor using interdigitated electrodes .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Using an optimized process of DNA probe preparation to minimize the effect of contaminants in commercial thiolated DNA probe ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"the electrode surface was functionalized with the 24-nucleotide DNA probes based on the West Nile virus sequence ( Kunjin strain ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"The biosensor has the ability to detect complementary DNA fragments with a detection limit down to 20 DNA target molecules ( 1.5 aM range ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"making it suitable for a practical point-of-care ( POC ) platform for low target count clinical applications without the need for amplification .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"The reproducibility of the biosensor detection was improved with efficient covalent immobilization of purified single-stranded DNA probe oligomers on cleaned gold microelectrodes .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"In addition to the low detection limit ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"the biosensor showed a dynamic range of detection from 1 mL À 1 to 10 5 mL À 1 target molecules ( 20 to 2 million targets ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"making it suitable for sample analysis in a typical clinical application environment .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"The binding results presented in this paper were validated using fluorescent oligomers .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}]}"}]}
{"paper_id": "463df0c159ec15f9da1cbd7d4397a397813977b1", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAlthough the structural diversity of sialic acid ( Sia ) is rapidly expanding , understanding of its biological significance has lagged behind . Advanced technologies to detect and probe diverse structures of Sia are absolutely necessary not only to understand further biological significance but also to pursue medicinal and industrial applications . Here we describe analytical methods for detection of Sia that have recently been developed or improved , with a special focus on 9-O-acetylated N-acetylneuraminic acid ( Neu5 ,9 Ac ) , N-glycolylneuraminic acid ( Neu5Gc ) , deaminoneuraminic acid ( Kdn ) , O-sulfated Sia ( SiaS ) , and di - , oligo - , and polysialic acid ( diSia/oligoSia/polySia ) in glycoproteins and glycolipids . Much more attention has been paid to these Sia and sialoglycoconjugates during the last decade , in terms of regulation of the immune system , neural development and function , tumorigenesis , and aging .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Although the structural diversity of sialic acid ( Sia ) is rapidly expanding ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"understanding of its biological significance has lagged behind .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Advanced technologies to detect and probe diverse structures of Sia are absolutely necessary not only to understand further biological significance but also to pursue medicinal and industrial applications .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Here we describe analytical methods for detection of Sia that have recently been developed or improved ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"with a special focus on 9-O-acetylated N-acetylneuraminic acid ( Neu5 ,9 Ac ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"N-glycolylneuraminic acid ( Neu5Gc ) ,\", \"label\": \"method\", \"decision_reference\": \"method.definition\", \"id\": 6}, {\"segment_text\": \"deaminoneuraminic acid ( Kdn ) ,\", \"label\": \"method\", \"decision_reference\": \"method.definition\", \"id\": 7}, {\"segment_text\": \"O-sulfated Sia ( SiaS ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"and di - , oligo - ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"and polysialic acid ( diSia/oligoSia/polySia ) in glycoproteins and glycolipids .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Much more attention has been paid to these Sia and sialoglycoconjugates during the last decade ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"in terms of regulation of the immune system ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"neural development and function , tumorigenesis , and aging .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}]}"}]}
{"paper_id": "f32df2b12c58f0e31b9a31c92c122b28b7b17aa3", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPorcine reproductive and respiratory syndrome virus ( PRRSV ) is an enveloped , positive-sense singlestranded RNA virus belonging to the Arteriviridae family . Arteriviruses and coronaviruses are grouped together in the order Nidovirales , based on similarities in genome organization and expression strategy . Over the past decade , crystal structures of several viral proteins , electron microscopic studies of the virion , as well as biochemical and in vivo studies on protein-protein interactions have led to a greatly increased understanding of PRRSV structural biology . At this point , crystal structures are available for the viral proteases NSP1 ␣ , NSP1 ␤ and NSP4 and the nucleocapsid protein , N . The NSP1 ␣ and NSP1 ␤ structures have revealed additional non-protease domains that may be involved in modulation of host functions . The N protein forms a dimer with a novel fold so far only seen in PRRSV and other nidoviruses . Cryo-electron tomographic studies have shown the three-dimensional organization of the PRRSV virion and suggest that the viral nucleocapsid has an asymmetric , linear arrangement , rather than the isometric core previously described . Together , these studies have revealed a closer structural relationship between arteri-and coronaviruses than previously anticipated .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Porcine reproductive and respiratory syndrome virus ( PRRSV ) is an enveloped ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"positive-sense singlestranded RNA virus belonging to the Arteriviridae family .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Arteriviruses and coronaviruses are grouped together in the order Nidovirales ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"based on similarities in genome organization and expression strategy .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Over the past decade , crystal structures of several viral proteins ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"electron microscopic studies of the virion ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"as well as biochemical and in vivo studies on protein-protein interactions have led to a greatly increased understanding of PRRSV structural biology .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"At this point , crystal structures are available for the viral proteases NSP1 ␣ ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"NSP1 ␤ and NSP4 and the nucleocapsid protein , N .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"The NSP1 ␣ and NSP1 ␤ structures have revealed additional non-protease domains that may be involved in modulation of host functions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The N protein forms a dimer with a novel fold so far only seen in PRRSV and other nidoviruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Cryo-electron tomographic studies have shown the three-dimensional organization of the PRRSV virion and suggest that the viral nucleocapsid has an asymmetric ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"linear arrangement , rather than the isometric core previously described .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Together , these studies have revealed a closer structural relationship between arteri-and coronaviruses than previously anticipated .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "512ad31f56a7be38e686f3864431191b0b9f659e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe hydroalcoholic extract of Punica granatum ( pomegranate ) leaves was previously demonstrated to be anti-inflammatory in a rat model of lipopolysaccharide - ( LPS - ) induced acute peritonitis . Here , we investigated the anti-inflammatory effects of the ethyl acetate fraction obtained from the pomegranate leaf hydroalcoholic extract ( EAFPg ) on the LPS-induced acute lung injury ( ALI ) mouse model . Male Swiss mice received either EAFPg at different doses or dexamethasone ( per os ) prior to LPS intranasal instillation . Vehicle-treated mice were used as controls . Animals were culled at 4 h after LPS challenge , and the bronchoalveolar lavage fluid ( BALF ) and lung samples were collected for analysis . EAFPg and kaempferol effects on NO and cytokine production by LPS-stimulated RAW 264.7 macrophages were also investigated . Pretreatment with EAFPg ( 100-300 mg/kg ) markedly reduced cell accumulation ( specially neutrophils ) and collagen deposition in the lungs of ALI mice . The same animals presented with reduced lung and BALF TNF-α and IL-1β expression in comparison with vehicle controls ( p < 0 05 ) . Additionally , incubation with either EAFPg or kaempferol ( 100 μg/ml ) reduced NO production and cytokine gene expression in cultured LPS-treated RAW 264.7 macrophages . Overall , these results demonstrate that the prophylactic treatment with EAFPg attenuates acute lung inflammation . We suggest this fraction may be useful in treating ALI .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The hydroalcoholic extract of Punica granatum ( pomegranate ) leaves was previously demonstrated to be anti-inflammatory in a rat model of lipopolysaccharide - ( LPS - ) induced acute peritonitis .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Here , we investigated the anti-inflammatory effects of the ethyl acetate fraction obtained from the pomegranate leaf hydroalcoholic extract ( EAFPg ) on the LPS-induced acute lung injury ( ALI ) mouse model .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"Male Swiss mice received either EAFPg at different doses or dexamethasone ( per os ) prior to LPS intranasal instillation .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Vehicle-treated mice were used as controls .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Animals were culled at 4 h after LPS challenge ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"and the bronchoalveolar lavage fluid ( BALF ) and lung samples were collected for analysis .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"EAFPg and kaempferol effects on NO and cytokine production by LPS-stimulated RAW 264.7 macrophages were also investigated .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Pretreatment with EAFPg ( 100-300 mg/kg ) markedly reduced cell accumulation ( specially neutrophils ) and collagen deposition in the lungs of ALI mice .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"The same animals presented with reduced lung and BALF TNF-α and IL-1β expression in comparison with vehicle controls ( p < 0 05 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Additionally , incubation with either EAFPg or kaempferol ( 100 μg/ml ) reduced NO production and cytokine gene expression in cultured LPS-treated RAW 264.7 macrophages .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Overall , these results demonstrate that the prophylactic treatment with EAFPg attenuates acute lung inflammation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"We suggest this fraction may be useful in treating ALI .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "dd8738920d2fdd2f606f249d47665b32dc33f1ea", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBovine Neonatal Pancytopenia ( BNP ) is a new emerging disease observed since 2007 in Germany and neighbouring countries . The syndrome affects newborn calves and is characterized by pancytopenia , severe bleeding and high lethality . So far , a causative role of infectious or toxic agents has been ruled out . Instead , the syndrome is induced after ingestion of colostrum , the first milk that supplies the calf with maternal antibodies . In analogy to similar diseases in humans it has therefore been postulated that BNP is caused by alloreactive , maternal antibodies . There is a striking association between BNP and a previous vaccination of the respective dams with a particular vaccine against Bovine Virus Diarrhoea ( BVD ) . This association has led to a suspension of the marketing authorisation for the vaccine , by the European Commission . The current study investigates the role of this vaccine in the pathogenesis of BNP . By flow cytometry we were able to demonstrate that sera of BNP dams ( dams that gave birth to a BNP calf ) harbour alloreactive antibodies binding to surface antigens on bovine leukocytes . A significantly weaker alloreactivity was observed with sera of non-BNP dams that have been vaccinated with the same vaccine but delivered healthy calves . No binding was seen with non-BVD-vaccinated control cows and animals that were vaccinated with other inactivated BVD vaccines so far not associated with BNP . The binding is functionally relevant , because opsonization of bovine leukocytes with alloantibodies led to an elevated cytophagocytosis by bovine macrophages . To test whether the vaccine induces alloreactive antibodies two strategies were employed : Guinea pigs were vaccinated with a panel of commercially available BVD-vaccines . Only the incriminated vaccine induced antibodies binding surface antigens on bovine leukocytes . Additionally , two calves were repeatedly vaccinated with the suspected vaccine and the development of alloreactivity was monitored . In dependence of the number of booster immunizations the induction of alloreactive antibodies could be observed . Finally , by affinity purification we were able to directly demonstrate that BNP associated alloantibodies cross react with the bovine kidney cell line used for vaccine production . Together this provides strong evidence that this particular BVD vaccine has the potential to induce BNP associated alloantibodies .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Bovine Neonatal Pancytopenia ( BNP ) is a new emerging disease observed since 2007 in Germany and neighbouring countries .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The syndrome affects newborn calves and is characterized by pancytopenia ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"severe bleeding and high lethality .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"So far , a causative role of infectious or toxic agents has been ruled out .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Instead , the syndrome is induced after ingestion of colostrum ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"the first milk that supplies the calf with maternal antibodies .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"In analogy to similar diseases in humans it has therefore been postulated that BNP is caused by alloreactive , maternal antibodies .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"There is a striking association between BNP and a previous vaccination of the respective dams with a particular vaccine against Bovine Virus Diarrhoea ( BVD ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"This association has led to a suspension of the marketing authorisation for the vaccine , by the European Commission .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"The current study investigates the role of this vaccine in the pathogenesis of BNP .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 10}, {\"segment_text\": \"By flow cytometry we were able to demonstrate that sera of BNP dams ( dams that gave birth to a BNP calf ) harbour alloreactive antibodies binding to surface antigens on bovine leukocytes .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"A significantly weaker alloreactivity was observed with sera of non-BNP dams that have been vaccinated with the same vaccine but delivered healthy calves .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"No binding was seen with non-BVD-vaccinated control cows and animals that were vaccinated with other inactivated BVD vaccines so far not associated with BNP .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"The binding is functionally relevant ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"because opsonization of bovine leukocytes with alloantibodies led to an elevated cytophagocytosis by bovine macrophages .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"To test whether the vaccine induces alloreactive antibodies two strategies were employed : Guinea pigs were vaccinated with a panel of commercially available BVD-vaccines .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 16}, {\"segment_text\": \"Only the incriminated vaccine induced antibodies binding surface antigens on bovine leukocytes .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Additionally , two calves were repeatedly vaccinated with the suspected vaccine and the development of alloreactivity was monitored .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 18}, {\"segment_text\": \"In dependence of the number of booster immunizations the induction of alloreactive antibodies could be observed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Finally , by affinity purification we were able to directly demonstrate that BNP associated alloantibodies cross react with the bovine kidney cell line used for vaccine production .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"Together this provides strong evidence that this particular BVD vaccine has the potential to induce BNP associated alloantibodies .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}]}"}]}
{"paper_id": "335f41145ff784047aa5a0ae829be50613c65038", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThis research examines whether maternal optimism/pessimism is associated with unplanned Cesarean section deliveries in China . If so , does the association remain after controlling for clinical factors associated with C-sections ? A sample of 227 mostly primiparous women in the third trimester of pregnancy was surveyed in a large tertiary care hospital in Beijing , China . Postdelivery data were collected from medical records . In bivariate analysis , both optimism and pessimism were related to unplanned c-section . However , when optimism and pessimism were entered into a regression model together , optimism was no longer statistically significant . Pessimism remained significant , even when adjusting for clinical factors such as previous abortion , previous miscarriage , pregnancy complications , infant gestational age , infant birthweight , labor duration , birth complications , and selfrated difficulty of the pregnancy . This research suggests that maternal mindset during pregnancy has a role in mode of delivery . However , more research is needed to elucidate potential causal pathways and test potential interventions .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"This research examines whether maternal optimism/pessimism is associated with unplanned Cesarean section deliveries in China .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"If so , does the association remain after controlling for clinical factors associated with C-sections ?\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"A sample of 227 mostly primiparous women in the third trimester of pregnancy was surveyed in a large tertiary care hospital in Beijing , China .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Postdelivery data were collected from medical records .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"In bivariate analysis , both optimism and pessimism were related to unplanned c-section .\", \"label\": \"method\", \"decision_reference\": \"boundary method_vs_finding\", \"id\": 5}, {\"segment_text\": \"However , when optimism and pessimism were entered into a regression model together ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"optimism was no longer statistically significant .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Pessimism remained significant , even when adjusting for clinical factors such as previous abortion ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"previous miscarriage , pregnancy complications ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"infant gestational age , infant birthweight ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"labor duration , birth complications ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and selfrated difficulty of the pregnancy .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"This research suggests that maternal mindset during pregnancy has a role in mode of delivery .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"However , more research is needed to elucidate potential causal pathways and test potential interventions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "0365a3d02ebf7e4718228be6c08db4c995481521", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRodent species are routinely presented to veterinary hospitals for wellness checks and different illnesses . When rodents are presented to the veterinarian for diagnosis and treatment , they deserve the same thorough approach that any other domestic species receives . The purpose of this article is to provide readers a review of the current information regarding examination , diagnosis , and treatment of some of the most common conditions for which rodent patients are presented . This article will cover 5 of the most common rodent species presented to veterinarians : guinea pigs , chinchillas , rats , mice , and hamsters .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Rodent species are routinely presented to veterinary hospitals for wellness checks and different illnesses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"When rodents are presented to the veterinarian for diagnosis and treatment ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"they deserve the same thorough approach that any other domestic species receives .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The purpose of this article is to provide readers a review of the current information regarding examination ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"diagnosis , and treatment of some of the most common conditions for which rodent patients are presented .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"This article will cover 5 of the most common rodent species presented to veterinarians : guinea pigs ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"chinchillas , rats , mice , and hamsters .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}]}"}]}
{"paper_id": "26273a8abe98bbeabfe8651fc433188c5f5b82c4", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nA b s t r a c t Objective : This paper presents a model designed to enable rapid detection and assessment of biological threats that may require swift intervention by the international public health community . We utilized Strauss ' grounded theory to develop an expanded model of social disruption due to biological events based on retrospective and prospective case studies . We then applied this model to the temporal domain and propose a heuristic staging model , the Wilson-Collmann Scale for assessing biological event evolution . We retrospectively and manually examined hard copy archival local media reports in the native vernacular for three biological events associated with substantial social disruption . The model was then tested prospectively through media harvesting based on keywords corresponding to the model parameters . : Our heuristic staging model provides valuable information about the features of a biological event that can be used to determine the level of concern warranted , such as whether the pathogen in question is responding to established public health disease control measures , including the use of antimicrobials or vaccines ; whether the public health and medical infrastructure of the country involved is adequate to mount the necessary response ; whether the country 's officials are providing an appropriate level of information to international public health authorities ; and whether the event poses a international threat . The approach is applicable for monitoring open-source ( public-domain ) media for indications and warnings of such events , and specifically for markers of the social disruption that commonly occur as these events unfold . These indications and warnings can then be used as the basis for staging the biological threat in the same manner that the United States National Weather Service currently uses storm warning models ( such as the Saffir-Simpson Hurricane Scale ) to detect and assess threatening weather conditions . Used as a complement to current epidemiological surveillance methods , our approach could aid global public health officials and national political leaders in responding to biological threats of international public health significance . Ⅲ J Am Med Inform Assoc. 2008 ; 15:158 -171 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"A b s t r a c t Objective : This paper presents a model designed to enable rapid detection and assessment of biological threats that may require swift intervention by the international public health community .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"We utilized Strauss ' grounded theory to develop an expanded model of social disruption due to biological events based on retrospective and prospective case studies .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"We then applied this model to the temporal domain and propose a heuristic staging model ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"the Wilson-Collmann Scale for assessing biological event evolution .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"We retrospectively and manually examined hard copy archival local media reports in the native vernacular for three biological events associated with substantial social disruption .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"The model was then tested prospectively through media harvesting based on keywords corresponding to the model parameters .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \": Our heuristic staging model provides valuable information about the features of a biological event that can be used to determine the level of concern warranted ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"such as whether the pathogen in question is responding to established public health disease control measures ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"including the use of antimicrobials or vaccines ; whether the public health and medical infrastructure of the country involved is adequate to mount the necessary response ; whether the country 's officials are providing an appropriate level of information to international public health authorities ; and whether the event poses a international threat .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"The approach is applicable for monitoring open-source ( public-domain ) media for indications and warnings of such events ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"and specifically for markers of the social disruption that commonly occur as these events unfold .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"These indications and warnings can then be used as the basis for staging the biological threat in the same manner that the United States National Weather Service currently uses storm warning models ( such as the Saffir-Simpson Hurricane Scale ) to detect and assess threatening weather conditions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Used as a complement to current epidemiological surveillance methods ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"our approach could aid global public health officials and national political leaders in responding to biological threats of international public health significance .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Ⅲ J Am Med Inform Assoc. 2008 ; 15:158 -171 .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 15}]}"}]}
{"paper_id": "d4f1ccfcf8b71a2828f39991e67142dd3a57fd1a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nLess than 20 sporadic cases of human Zika virus ( ZIKV ) infection were reported in Africa and Asia before 2007 , but large outbreaks involving up to 73 % of the populations on the Pacific islands have started since 2007 , and spread to the Americas in 2014 . Moreover , the clinical manifestation of ZIKV infection has apparently changed , as evident by increasing reports of neurological complications , such as Guillain-Barré syndrome in adults and congenital anomalies in neonates . We comprehensively compared the genome sequences of pre-epidemic and epidemic ZIKV strains with complete genome or complete polyprotein sequences available in GenBank . Besides the reported phylogenetic clustering of the epidemic strains with the Asian lineage , we found that the topology of phylogenetic tree of all coding regions is the same except that of the non-structural 2B ( NS2B ) coding region . This finding was confirmed by bootscan analysis and multiple sequence alignment , which suggested the presence of a fragment of genetic recombination at NS2B with that of Spondweni virus . Moreover , the representative epidemic strain possesses one large bulge of nine bases instead of an external loop on the first stem-loop structure at the 3ʹ-untranslated region just distal to the stop codon of the NS5 in the 1947 pre-epidemic prototype strain . Fifteen amino acid substitutions are found in the epidemic strains when compared with the pre-epidemic strains . As mutations in other flaviviruses can be associated with changes in virulence , replication efficiency , antigenic epitopes and host tropism , further studies would be important to ascertain the biological significance of these genomic changes .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Less than 20 sporadic cases of human Zika virus ( ZIKV ) infection were reported in Africa and Asia before 2007 ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"but large outbreaks involving up to 73 % of the populations on the Pacific islands have started since 2007 ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"and spread to the Americas in 2014 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Moreover , the clinical manifestation of ZIKV infection has apparently changed ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"as evident by increasing reports of neurological complications ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"such as Guillain-Barré syndrome in adults and congenital anomalies in neonates .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"We comprehensively compared the genome sequences of pre-epidemic and epidemic ZIKV strains with complete genome or complete polyprotein sequences available in GenBank .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Besides the reported phylogenetic clustering of the epidemic strains with the Asian lineage ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"we found that the topology of phylogenetic tree of all coding regions is the same except that of the non-structural 2B ( NS2B ) coding region .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"This finding was confirmed by bootscan analysis and multiple sequence alignment ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"which suggested the presence of a fragment of genetic recombination at NS2B with that of Spondweni virus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Moreover , the representative epidemic strain possesses one large bulge of nine bases instead of an external loop on the first stem-loop structure at the 3ʹ-untranslated region just distal to the stop codon of the NS5 in the 1947 pre-epidemic prototype strain .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Fifteen amino acid substitutions are found in the epidemic strains when compared with the pre-epidemic strains .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"As mutations in other flaviviruses can be associated with changes in virulence ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"replication efficiency , antigenic epitopes and host tropism ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"further studies would be important to ascertain the biological significance of these genomic changes .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "63c9324f0d9297dca61f7f9997d7f1857d7e2a32", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPrevention of zoonoses in cancer patients is the theme of this chapter and it is hoped that it will encourage and help doctors caring for such patients to educate them to avoid the infections . Avoidance need not include separation from a pet or occupation or recreation , but the use of caution conditioned by knowledge of the sources of infection and the ways we contact them should lead to effective prevention .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Prevention of zoonoses in cancer patients is the theme of this chapter and it is hoped that it will encourage and help doctors caring for such patients to educate them to avoid the infections .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Avoidance need not include separation from a pet or occupation or recreation ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"but the use of caution conditioned by knowledge of the sources of infection and the ways we contact them should lead to effective prevention .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}]}"}]}
{"paper_id": "27869d617d1c3766400b9f33f31e28f8fb1bdbd0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nHaemophilus parasuis ( HPS ) is an important swine pathogen that causes Glässer 's disease , which is characterized by fibrinous polyserositis , meningitis and arthritis . The molecular mechanisms that underlie the pathogenesis of the disease remain poorly understood , particularly the resistance of porcine immune system to HPS invasion . In this study , we investigated the global changes in gene expression in the spleen following HPS infection using the Affymetrix Porcine Genechip ™ . Results : A total of 931 differentially expressed ( DE ) transcripts were identified in the porcine spleen 7 days after HPS infection ; of these , 92 unique genes showed differential expression patterns based on analysis using BLASTX and Gene Ontology . The DE genes involved in the immune response included genes for inflammasomes ( RETN , S100A8 , S100A9 , S100A12 ) , adhesion molecules ( CLDN3 , CSPG2 , CD44 , LGALS8 ) , transcription factors ( ZBTB16 , SLC39A14 , CEBPD , CEBPB ) , acute-phase proteins and complement ( SAA1 , LTF , HP , C3 ) , differentiation genes for epithelial cells and keratinocytes ( TGM1 , MS4A8B , CSTA ) , and genes related to antigen processing and presentation ( HLA-B , HLA-DRB1 ) . Further immunostimulation analyses indicated that mRNA levels of S100A8 , S100A9 , and S100A12 in porcine PK-15 cells increased within 48 h and were sustained after administration of lipopolysaccharide ( LPS ) and Poly ( I : C ) respectively . In addition , mapping of DE genes to porcine health traits QTL regions showed that 70 genes were distributed in 7 different known porcine QTL regions . Finally , 10 DE genes were validated by quantitative PCR . Our findings demonstrate previously unrecognized changes in gene transcription that are associated with HPS infection in vivo , and many potential cascades identified in the study clearly merit further investigation . Our data provide new clues to the nature of the immune response in mammals , and we have identified candidate genes that are related to resistance to HPS .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Haemophilus parasuis ( HPS ) is an important swine pathogen that causes Glässer 's disease ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"which is characterized by fibrinous polyserositis , meningitis and arthritis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The molecular mechanisms that underlie the pathogenesis of the disease remain poorly understood ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"particularly the resistance of porcine immune system to HPS invasion .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"In this study , we investigated the global changes in gene expression in the spleen following HPS infection using the Affymetrix Porcine Genechip ™ .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Results : A total of 931 differentially expressed ( DE ) transcripts were identified in the porcine spleen 7 days after HPS infection ; of these ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"92 unique genes showed differential expression patterns based on analysis using BLASTX and Gene Ontology .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"The DE genes involved in the immune response included genes for inflammasomes ( RETN , S100A8 , S100A9 , S100A12 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"adhesion molecules ( CLDN3 , CSPG2 , CD44 , LGALS8 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"transcription factors ( ZBTB16 , SLC39A14 , CEBPD , CEBPB ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"acute-phase proteins and complement ( SAA1 , LTF , HP , C3 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"differentiation genes for epithelial cells and keratinocytes ( TGM1 , MS4A8B , CSTA ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"and genes related to antigen processing and presentation ( HLA-B , HLA-DRB1 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Further immunostimulation analyses indicated that mRNA levels of S100A8 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"S100A9 , and S100A12 in porcine PK-15 cells increased within 48 h and were sustained after administration of lipopolysaccharide ( LPS ) and Poly ( I : C ) respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"In addition , mapping of DE genes to porcine health traits QTL regions showed that 70 genes were distributed in 7 different known porcine QTL regions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Finally , 10 DE genes were validated by quantitative PCR .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Our findings demonstrate previously unrecognized changes in gene transcription that are associated with HPS infection in vivo ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"and many potential cascades identified in the study clearly merit further investigation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Our data provide new clues to the nature of the immune response in mammals ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"and we have identified candidate genes that are related to resistance to HPS .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}]}"}]}
{"paper_id": "71587e25a9e61a1d6b0ddd3d878f51278844212d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRotavirus is a non-enveloped virus that depends on cellular lipids for cell entry and associates with lipid rafts during assembly . However , the effects of cellular lipids on rotavirus assembly are still not fully understood . The present study analyzes the effects of lovastatin , an inhibitor of cholesterol biosynthesis , during rotavirus infection in MA104 cells with regard to viral growth and particle assembly . Following viral infection , a 2-log relative reduction of viral titers was observed in drug-treated cells , while viral mRNA levels in infected cells remained unaltered in both groups . Furthermore , the levels of some viral proteins in drug-treated cells were elevated . The observed discordance between the viral RNA and protein levels and the decrease in infectivity titers of viral progeny in the drug-treated cells suggested that the drug affects viral assembly , the viral proteins not being properly incorporated into virions . Transmission electron microscopic ( TEM ) analysis revealed that in drug-treated cells there was an increase in `` empty-looking '' rotavirus particles devoid of an electron-dense core as compared to the normal , electron-dense particles seen in untreated infected cells . The present study thus provides visual evidence of defective rotavirus particle assembly as a result of cholesterol depletion .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Rotavirus is a non-enveloped virus that depends on cellular lipids for cell entry and associates with lipid rafts during assembly .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"However , the effects of cellular lipids on rotavirus assembly are still not fully understood .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The present study analyzes the effects of lovastatin ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"an inhibitor of cholesterol biosynthesis ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"during rotavirus infection in MA104 cells with regard to viral growth and particle assembly .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Following viral infection , a 2-log relative reduction of viral titers was observed in drug-treated cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"while viral mRNA levels in infected cells remained unaltered in both groups .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Furthermore , the levels of some viral proteins in drug-treated cells were elevated .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"The observed discordance between the viral RNA and protein levels and the decrease in infectivity titers of viral progeny in the drug-treated cells suggested that the drug affects viral assembly ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"the viral proteins not being properly incorporated into virions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Transmission electron microscopic ( TEM ) analysis revealed that in drug-treated cells there was an increase in `` empty-looking '' rotavirus particles devoid of an electron-dense core as compared to the normal ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"electron-dense particles seen in untreated infected cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"The present study thus provides visual evidence of defective rotavirus particle assembly as a result of cholesterol depletion .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "a06b054ac060108a8563363fa40ce617eb7af258", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIndustrial hygiene specialists from the National Institute for Occupational Safety and Health ( NIOSH ) visited hospitals and medical centers throughout Taiwan . They assisted with designing and evaluating ventilation modifications for infection control , developed guidelines for converting hospital rooms into SARS patient isolation rooms , prepared designs for the rapid conversion of a vacated military facility into a SARS screening and observation facility , assessed environmental aspects of dedicated SARS hospitals , and worked in concert with the Taiwanese to develop hospital ventilation guidelines . We describe the environmental findings and observations from this response , including the rapid reconfiguration of medical facilities during a national health emergency , and discuss environmental challenges should SARS or a SARS-like virus emerge again .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Industrial hygiene specialists from the National Institute for Occupational Safety and Health ( NIOSH ) visited hospitals and medical centers throughout Taiwan .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"They assisted with designing and evaluating ventilation modifications for infection control ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"developed guidelines for converting hospital rooms into SARS patient isolation rooms ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"prepared designs for the rapid conversion of a vacated military facility into a SARS screening and observation facility ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"assessed environmental aspects of dedicated SARS hospitals ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"and worked in concert with the Taiwanese to develop hospital ventilation guidelines .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"We describe the environmental findings and observations from this response ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"including the rapid reconfiguration of medical facilities during a national health emergency ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and discuss environmental challenges should SARS or a SARS-like virus emerge again .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}]}"}]}
{"paper_id": "2a2a3087f3f753cbfdab460a0a31c0ac64b0cc52", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMany economically important cattle diseases spread between herds through livestock movements . Traditionally , most transmission models have assumed that all purchased cattle carry the same risk of generating outbreaks in the destination herd . Using data on bovine viral diarrhoea virus ( BVDV ) in Scotland as a case example , this study provides empirical and theoretical evidence that the risk of disease transmission varies substantially based on the animal and herd demographic characteristics at the time of purchase . Multivariable logistic regression analysis revealed that purchasing pregnant heifers and open cows sold with a calf at foot were associated with an increased risk of beef herds being seropositive for BVDV . Based on the results from a dynamic within-herd simulation model , these findings may be partly explained by the age-related probability of animals being persistently infected with BVDV as well as the herd demographic structure at the time of animal introductions . There was also evidence that an epidemiologically important network statistic , `` betweenness centrality '' ( a measure frequently associated with the potential for herds to acquire and transmit disease ) , was significantly higher for herds that supplied these particular types of replacement beef cattle . The trends for dairy herds were not as clear , although there was some evidence that open heifers and open lactating cows were associated with an increased risk of BVDV . Overall , these findings have important implications for developing simulation models that more accurately reflect the industry-level transmission dynamics of infectious cattle diseases .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Many economically important cattle diseases spread between herds through livestock movements .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Traditionally , most transmission models have assumed that all purchased cattle carry the same risk of generating outbreaks in the destination herd .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Using data on bovine viral diarrhoea virus ( BVDV ) in Scotland as a case example ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"this study provides empirical and theoretical evidence that the risk of disease transmission varies substantially based on the animal and herd demographic characteristics at the time of purchase .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Multivariable logistic regression analysis revealed that purchasing pregnant heifers and open cows sold with a calf at foot were associated with an increased risk of beef herds being seropositive for BVDV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Based on the results from a dynamic within-herd simulation model ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"these findings may be partly explained by the age-related probability of animals being persistently infected with BVDV as well as the herd demographic structure at the time of animal introductions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"There was also evidence that an epidemiologically important network statistic ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"`` betweenness centrality '' ( a measure frequently associated with the potential for herds to acquire and transmit disease ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"was significantly higher for herds that supplied these particular types of replacement beef cattle .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The trends for dairy herds were not as clear ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"although there was some evidence that open heifers and open lactating cows were associated with an increased risk of BVDV .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"Overall , these findings have important implications for developing simulation models that more accurately reflect the industry-level transmission dynamics of infectious cattle diseases .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "f82f0dbdf2cb656cff96dbf88a0a0e3893305aa9", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : SARS-CoV entry into target cells is a unique and complex process . Results : Cell entry mediated by SARS-CoV S was strongly inhibited after knockdown of PI4KB . Conclusion : PI4KB is required for SARS-CoV S-mediated entry , and this function is dependent on its kinase activity . Significance : Our results indicate a new function for PI4KB and suggest a new drug target for preventing SARS-CoV infection . Further research suggested that PI4P plays an essential role in SARS-CoV spike-mediated entry , which is regulated by the PI4P lipid microenvironment . We further demonstrate that PI4KB does not affect virus entry at the SARS-CoV S-ACE2 binding interface or at the stage of virus internalization but rather at or before virus fusion . Taken together , these results indicate a new function for PI4KB and suggest a new drug target for preventing SARS-CoV infection .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : SARS-CoV entry into target cells is a unique and complex process .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Results : Cell entry mediated by SARS-CoV S was strongly inhibited after knockdown of PI4KB .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"Conclusion : PI4KB is required for SARS-CoV S-mediated entry ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 3}, {\"segment_text\": \"and this function is dependent on its kinase activity .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 4}, {\"segment_text\": \"Significance : Our results indicate a new function for PI4KB and suggest a new drug target for preventing SARS-CoV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"Further research suggested that PI4P plays an essential role in SARS-CoV spike-mediated entry ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"which is regulated by the PI4P lipid microenvironment .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"We further demonstrate that PI4KB does not affect virus entry at the SARS-CoV S-ACE2 binding interface or at the stage of virus internalization but rather at or before virus fusion .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"Taken together , these results indicate a new function for PI4KB and suggest a new drug target for preventing SARS-CoV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}]}"}]}
{"paper_id": "4c2d326a10d98f8f503f8df460291e059cc77a75", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Since late 2013 , porcine epidemic diarrhea virus ( PEDV ) has reemerged in Japan and caused severe economic losses to the swine industry . Although PEDV vaccines have been used widely , the disease has swept rapidly across the county , and is commonly observed in PED-vaccinated farms , and has recurred in domestic herds . To better understand PEDVs responsible for the reemerging outbreaks in Japan , full-length spike ( S ) , membrane ( M ) , and nucleocapsid ( N ) genes of 45 PEDVs collected in Japan during 2013-2016 , were sequenced and analyzed . Results : Phylogenetic analysis based on S gene sequences revealed that all the recent field PEDVs were genetically distinct from the classical Japanese strains , and were classified into three genotypes : North American ( NA ) , S INDEL , and Asian non-S INDEL . Our data suggested a possibility that multiple parental PEDV strains were introduced into Japan from abroad at the same time or similar times . The newly identified Japanese strains showed the closest relationship to the US strains . Two sublineages of Japanese strains circulating in Japan were similar to two sublineages identified in the US , suggesting common ancestors for these strains . In comparison with two vaccine strains used in Japan , the field strains had various changes in epitope regions , glycosylation sites , and phosphorylation sites . These substitutions , particularly observed in epitope regions of the S ( 521 , 553 , 568 , and 570 ) , M ( 5 ) , and N ( 123 , 252 , and 255 ) proteins , may have affected antigenicity and vaccine efficacy , resulting in an unsuccessful PEDV control . Sequence comparisons between PEDVs collected from primary and secondary outbreaks in three herds revealed that the disease has developed to an endemic stage in which PEDV could persist for nearly two years in the herds or local regions , causing subsequent epidemics . Conclusions : These results elucidate the genetic characteristics , origin , and molecular epidemiology of PEDVs circulating in Japan , as well as the PEDV strains causing recurrent outbreaks . This study provides a better insight into the PEDVs responsible for recent outbreaks in Japan , and could potentially help to develop measures for controlling and preventing the disease .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Since late 2013 ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"porcine epidemic diarrhea virus ( PEDV ) has reemerged in Japan and caused severe economic losses to the swine industry .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Although PEDV vaccines have been used widely ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"the disease has swept rapidly across the county ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"and is commonly observed in PED-vaccinated farms ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"and has recurred in domestic herds .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"To better understand PEDVs responsible for the reemerging outbreaks in Japan ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"full-length spike ( S ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"membrane ( M ) , and nucleocapsid ( N ) genes of 45 PEDVs collected in Japan during 2013-2016 , were sequenced and analyzed .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Results : Phylogenetic analysis based on S gene sequences revealed that all the recent field PEDVs were genetically distinct from the classical Japanese strains ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"and were classified into three genotypes : North American ( NA ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"S INDEL , and Asian non-S INDEL .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Our data suggested a possibility that multiple parental PEDV strains were introduced into Japan from abroad at the same time or similar times .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"The newly identified Japanese strains showed the closest relationship to the US strains .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"Two sublineages of Japanese strains circulating in Japan were similar to two sublineages identified in the US ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"suggesting common ancestors for these strains .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"In comparison with two vaccine strains used in Japan ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"the field strains had various changes in epitope regions ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"glycosylation sites , and phosphorylation sites .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"These substitutions , particularly observed in epitope regions of the S ( 521 , 553 , 568 , and 570 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}, {\"segment_text\": \"M ( 5 ) , and N ( 123 , 252 , and 255 ) proteins ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}, {\"segment_text\": \"may have affected antigenicity and vaccine efficacy ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 22}, {\"segment_text\": \"resulting in an unsuccessful PEDV control .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 23}, {\"segment_text\": \"Sequence comparisons between PEDVs collected from primary and secondary outbreaks in three herds revealed that the disease has developed to an endemic stage in which PEDV could persist for nearly two years in the herds or local regions , causing subsequent epidemics .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 24}, {\"segment_text\": \"Conclusions : These results elucidate the genetic characteristics ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 25}, {\"segment_text\": \"origin , and molecular epidemiology of PEDVs circulating in Japan ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 26}, {\"segment_text\": \"as well as the PEDV strains causing recurrent outbreaks .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 27}, {\"segment_text\": \"This study provides a better insight into the PEDVs responsible for recent outbreaks in Japan ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 28}, {\"segment_text\": \"and could potentially help to develop measures for controlling and preventing the disease .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 29}]}"}]}
{"paper_id": "c583cb0e46a3eff4eba037b683b3ef1f5f8629b7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\npublicly funded repositories , such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source . These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active . Fig 1 . Standardized mean difference ( SMD ) and 95 % confidence interval ( 95 % CI ) of cardiac troponin I ( cTnI ) values in coronavirus disease 2019 ( COVID-19 ) patients with or without severe disease .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"publicly funded repositories , such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Fig 1 .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 3}, {\"segment_text\": \"Standardized mean difference ( SMD ) and 95 % confidence interval ( 95 % CI ) of cardiac troponin I ( cTnI ) values in coronavirus disease 2019 ( COVID-19 ) patients with or without severe disease .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 4}]}"}]}
{"paper_id": "b980feb6620f08f7958009ae3ef0bbc417162f58", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Human rhinoviruses ( HRVs ) are a well-recognized cause of long-term care home ( LTCH ) outbreaks of respiratory illness . However , there are limited data on the molecular epidemiology of the HRV types involved . Objectives : To determine whether a large respiratory outbreak in a LTCH was caused by a single type of HRV , and to describe the clinical impact of the outbreak . Study design : Nasopharyngeal swabs were collected from residents with one or more of the following : fever , cough , rhinitis , or congestion . Specimens were interrogated by multiplex PCR using the ResPlex II assay . Samples positive for HRV were then submitted for genotyping by partial sequence analysis of the 5 untranslated ( UTR ) and viral protein ( VP ) 1 capsid regions . Results : Of 71 screened , 56 residents were positive for a HRV during an outbreak that lasted 5.5 weeks ; 27 healthcare workers also had respiratory symptoms . Three residents were transferred to hospital and 2 died . Seven units in two wings of the LTCH were affected , resulting in 3152.5 resident unit closure days . Three different HRV genotypes were identified , although HRV-A1 dominated . Conclusions : This large outbreak of HRVs among residents and healthcare workers in a LTCH was associated with substantial resident and staff morbidity as well as significant unit closures . Multiple types of HRV were implicated but an HRV-A1 type dominated , warranting further investigation into viral determinants for virulence and transmission .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Human rhinoviruses ( HRVs ) are a well-recognized cause of long-term care home ( LTCH ) outbreaks of respiratory illness .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"However , there are limited data on the molecular epidemiology of the HRV types involved .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Objectives : To determine whether a large respiratory outbreak in a LTCH was caused by a single type of HRV ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"and to describe the clinical impact of the outbreak .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Study design : Nasopharyngeal swabs were collected from residents with one or more of the following : fever ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"cough , rhinitis , or congestion .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Specimens were interrogated by multiplex PCR using the ResPlex II assay .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Samples positive for HRV were then submitted for genotyping by partial sequence analysis of the 5 untranslated ( UTR ) and viral protein ( VP ) 1 capsid regions .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Results : Of 71 screened ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"56 residents were positive for a HRV during an outbreak that lasted 5.5 weeks ; 27 healthcare workers also had respiratory symptoms .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"Three residents were transferred to hospital and 2 died .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"Seven units in two wings of the LTCH were affected ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"resulting in 3152.5 resident unit closure days .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"Three different HRV genotypes were identified , although HRV-A1 dominated .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"Conclusions : This large outbreak of HRVs among residents and healthcare workers in a LTCH was associated with substantial resident and staff morbidity as well as significant unit closures .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Multiple types of HRV were implicated but an HRV-A1 type dominated ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"warranting further investigation into viral determinants for virulence and transmission .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "19fac1b4b535f073170a501d42273e8124861bf0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPublic health service Health insurance s u m m a r y As one of the fastest growing cities in Pearl River Delta of southern China , Shenzhen accommodates a higher percentage and increasing number of internal migrants , mainly coming from the inland areas . The public health issues that challenge its local government include the special population structure , high incidence of infectious diseases , high prevalence of mental problems , rising chronic disease burdens , and maternal and children 's health issues , although progress has been made in the past years . The health authority of Shenzhen has realized that provision of high quality equitable public health services to its residents , including migrants is of high priority , and should be supported by innovations in the health insurance system and establishment of community-based primary care networks . Making changes within the national-level health reform framework and learning from international experiences are necessary and important .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Public health service\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Health insurance s u m m a r y As one of the fastest growing cities in Pearl River Delta of southern China ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Shenzhen accommodates a higher percentage and increasing number of internal migrants ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"mainly coming from the inland areas .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"The public health issues that challenge its local government include the special population structure ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"high incidence of infectious diseases ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"high prevalence of mental problems ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"rising chronic disease burdens , and maternal and children 's health issues ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"although progress has been made in the past years .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"The health authority of Shenzhen has realized that provision of high quality equitable public health services to its residents ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"including migrants is of high priority ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"and should be supported by innovations in the health insurance system and establishment of community-based primary care networks .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"Making changes within the national-level health reform framework and learning from international experiences are necessary and important .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "b35c5f90e09d90f6fd6cff9dab355755e4c33fe4", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Whether information sources influence health protective behaviours during influenza pandemics or other emerging infectious disease epidemics is uncertain . Methodology : Data from cross-sectional telephone interviews of 1,001 Hong Kong adults in June , 2009 were tested against theory and data-derived hypothesized associations between trust in ( formal/informal ) information , understanding , selfefficacy , perceived susceptibility and worry , and hand hygiene and social distancing using Structural Equation Modelling with multigroup comparisons . Principal Findings : Trust in formal ( government/media ) information about influenza was associated with greater reported understanding of A/H1N1 cause ( b = 0.36 ) and A/H1N1 prevention self-efficacy ( b = 0.25 ) , which in turn were associated with more hand hygiene ( b = 0.19 and b = 0.23 , respectively ) . Trust in informal ( interpersonal ) information was negatively associated with perceived personal A/H1N1 susceptibility ( b = 20.21 ) , which was negatively associated with perceived selfefficacy ( b = 20.42 ) but positively associated with influenza worry ( b = 0.44 ) . Trust in informal information was positively associated with influenza worry ( b = 0.16 ) which was in turn associated with greater social distancing ( b = 0.36 ) . Multigroup comparisons showed gender differences regarding paths from trust in formal information to understanding of A/H1N1 cause , trust in informal information to understanding of A/H1N1 cause , and understanding of A/H1N1 cause to perceived self-efficacy . Conclusions/Significance : Trust in government/media information was more strongly associated with greater self-efficacy and handwashing , whereas trust in informal information was strongly associated with perceived health threat and avoidance behaviour . Risk communication should consider the effect of gender differences .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Whether information sources influence health protective behaviours during influenza pandemics or other emerging infectious disease epidemics is uncertain .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Methodology : Data from cross-sectional telephone interviews of 1,001 Hong Kong adults in June ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"2009 were tested against theory and data-derived hypothesized associations between trust in ( formal/informal ) information ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"understanding , selfefficacy , perceived susceptibility and worry ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"and hand hygiene and social distancing using Structural Equation Modelling with multigroup comparisons .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Principal Findings : Trust in formal ( government/media ) information about influenza was associated with greater reported understanding of A/H1N1 cause ( b = 0.36 ) and A/H1N1 prevention self-efficacy ( b = 0.25 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"which in turn were associated with more hand hygiene ( b = 0.19 and b = 0.23 , respectively ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"Trust in informal ( interpersonal ) information was negatively associated with perceived personal A/H1N1 susceptibility ( b = 20.21 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"which was negatively associated with perceived selfefficacy ( b = 20.42 ) but positively associated with influenza worry ( b = 0.44 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Trust in informal information was positively associated with influenza worry ( b = 0.16 ) which was in turn associated with greater social distancing ( b = 0.36 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"Multigroup comparisons showed gender differences regarding paths from trust in formal information to understanding of A/H1N1 cause ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"trust in informal information to understanding of A/H1N1 cause ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"and understanding of A/H1N1 cause to perceived self-efficacy .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"Conclusions/Significance : Trust in government/media information was more strongly associated with greater self-efficacy and handwashing ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"whereas trust in informal information was strongly associated with perceived health threat and avoidance behaviour .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"Risk communication should consider the effect of gender differences .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}]}"}]}
{"paper_id": "32d5b5c7b38c1dd14b316de97bce86e5ab252f91", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Dengue , caused by one of the four serologically distinct dengue viruses ( DENV-1 to − 4 ) , is a mosquito-borne disease of serious global health significance . Reliable and cost-effective diagnostic tests , along with effective vaccines and vector-control strategies , are highly required to reduce dengue morbidity and mortality . Evaluation studies revealed that many commercially available NS1 antigen ( Ag ) tests have limited sensitivity to DENV-4 serotype compared to the other three serotypes . These studies indicated the need for development of new NS1 Ag detection test with improved sensitivity to DENV-4 . An NS1 capture enzyme linked immunoassay ( ELISA ) specific to DENV-4 may improve the detection of DENV-4 cases worldwide . In addition , a serotype-specific NS1 Ag test identifies both DENV and the infecting serotype . Methods : In this study , we used a small-ubiquitin-like modifier ( SUMO * ) cloning vector to express a SUMO * - DENV-4 rNS1 fusion protein to develop NS1 DENV-4 specific monoclonal antibodies ( MAbs ) . These newly developed MAbs were then optimized for use in an anti-NS1 DENV-4 capture ELISA . The serotype specificity and sensitivity of this ELISA was evaluated using ( i ) supernatants from DENV ( 1-4 ) - infected Vero cell cultures , ( ii ) rNS1s from all the four DENV ( 1-4 ) and , ( iii ) rNS1s of related flaviviruses ( yellow fever virus ; YFV and West Nile virus ; WNV ) . Results : From the evaluation studies of the newly developed MAbs , we identified three DENV-4 specific anti-NS1 MAbs : 3H7A9 , 8A6F2 and 6D4B10 . Two of these MAbs were optimal for use in a DENV-4 serotype-specific NS1 capture ELISA : MAb 8A6F2 as the capture antibody and 6D4B10 as a detection antibody . Conclusion : This ELISA was sensitive and specific to DENV-4 with no cross-reactivity to other three DENV ( 1-3 ) serotypes and other heterologous flaviviruses . Taken together these data indicated that our MAbs are useful reagents for the development of DENV-4 immunodiagnostic tests .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Dengue , caused by one of the four serologically distinct dengue viruses ( DENV-1 to − 4 ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"is a mosquito-borne disease of serious global health significance .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Reliable and cost-effective diagnostic tests ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"along with effective vaccines and vector-control strategies ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"are highly required to reduce dengue morbidity and mortality .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Evaluation studies revealed that many commercially available NS1 antigen ( Ag ) tests have limited sensitivity to DENV-4 serotype compared to the other three serotypes .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"These studies indicated the need for development of new NS1 Ag detection test with improved sensitivity to DENV-4 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"An NS1 capture enzyme linked immunoassay ( ELISA ) specific to DENV-4 may improve the detection of DENV-4 cases worldwide .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"In addition , a serotype-specific NS1 Ag test identifies both DENV and the infecting serotype .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"Methods : In this study ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"we used a small-ubiquitin-like modifier ( SUMO * ) cloning vector to express a SUMO * - DENV-4 rNS1 fusion protein to develop NS1 DENV-4 specific monoclonal antibodies ( MAbs ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"These newly developed MAbs were then optimized for use in an anti-NS1 DENV-4 capture ELISA .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"The serotype specificity and sensitivity of this ELISA was evaluated using ( i ) supernatants from DENV ( 1-4 ) - infected Vero cell cultures ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"( ii ) rNS1s from all the four DENV ( 1-4 ) and ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"( iii ) rNS1s of related flaviviruses ( yellow fever virus ; YFV and West Nile virus ; WNV ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 15}, {\"segment_text\": \"Results : From the evaluation studies of the newly developed MAbs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"we identified three DENV-4 specific anti-NS1 MAbs : 3H7A9 , 8A6F2 and 6D4B10 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Two of these MAbs were optimal for use in a DENV-4 serotype-specific NS1 capture ELISA : MAb 8A6F2 as the capture antibody and 6D4B10 as a detection antibody .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Conclusion : This ELISA was sensitive and specific to DENV-4 with no cross-reactivity to other three DENV ( 1-3 ) serotypes and other heterologous flaviviruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Taken together these data indicated that our MAbs are useful reagents for the development of DENV-4 immunodiagnostic tests .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}]}"}]}
{"paper_id": "c5fa97f3c08e5b88b1081d261c675cf9f0fea73b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nWe conducted a challenge/rechallenge trial in which 3 alpacas were infected with Middle East respiratory syndrome coronavirus . The alpacas shed virus at challenge but were refractory to further shedding at rechallenge on day 21 . The trial indicates that alpacas may be suitable models for infection and shedding dynamics of this virus .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"We conducted a challenge/rechallenge trial in which 3 alpacas were infected with Middle East respiratory syndrome coronavirus .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 1}, {\"segment_text\": \"The alpacas shed virus at challenge but were refractory to further shedding at rechallenge on day 21 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"The trial indicates that alpacas may be suitable models for infection and shedding dynamics of this virus .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 3}]}"}]}
{"paper_id": "3273d1af75cb33dbbec0d61dded9d576fe946030", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIndividual genes or regions are still commonly used to estimate the phylogenetic relationships among viral isolates . The genomic regions that can faithfully provide assessments consistent with those predicted with full-length genome sequences would be preferable to serve as good candidates of the phylogenetic markers for molecular epidemiological studies of many viruses . Here we employed a statistical method to evaluate the evolutionary relationships between individual viral genes and full-length genomes without tree construction as a way to determine which gene can match the genome well in phylogenetic analyses . This method was performed by calculation of linear correlations between the genetic distance matrices of aligned individual gene sequences and aligned genome sequences . We applied this method to the phylogenetic analyses of porcine circovirus 2 ( PCV2 ) , measles virus ( MV ) , hepatitis E virus ( HEV ) and Japanese encephalitis virus ( JEV ) . Phylogenetic trees were constructed for comparisons and the possible factors affecting the method accuracy were also discussed in the calculations . The results revealed that this method could produce results consistent with those of previous studies about the proper consensus sequences that could be successfully used as phylogenetic markers . And our results also suggested that these evolutionary correlations could provide useful information for identifying genes that could be used effectively to infer the genetic relationships .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Individual genes or regions are still commonly used to estimate the phylogenetic relationships among viral isolates .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"The genomic regions that can faithfully provide assessments consistent with those predicted with full-length genome sequences would be preferable to serve as good candidates of the phylogenetic markers for molecular epidemiological studies of many viruses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Here we employed a statistical method to evaluate the evolutionary relationships between individual viral genes and full-length genomes without tree construction as a way to determine which gene can match the genome well in phylogenetic analyses .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"This method was performed by calculation of linear correlations between the genetic distance matrices of aligned individual gene sequences and aligned genome sequences .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"We applied this method to the phylogenetic analyses of porcine circovirus 2 ( PCV2 ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"measles virus ( MV ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"hepatitis E virus ( HEV ) and Japanese encephalitis virus ( JEV ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Phylogenetic trees were constructed for comparisons and the possible factors affecting the method accuracy were also discussed in the calculations .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The results revealed that this method could produce results consistent with those of previous studies about the proper consensus sequences that could be successfully used as phylogenetic markers .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"And our results also suggested that these evolutionary correlations could provide useful information for identifying genes that could be used effectively to infer the genetic relationships .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "380afa473441d4d993bcd07fe9b73452dc026b57", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAlthough flaviviruses encode their own helicases , evidence suggests that cellular helicases are also required for replication and/or assembly of these viruses . By and large , the mechanisms of action for viral and cellular helicases are not known . Moreover , in some cases , enzymatic activity is not even required for their roles in virus biology . Recently , we showed that expression of the host nucleolar helicase DDX56 is important for infectivity of West Nile virus ( WNV ) particles . In the present study , we demonstrate that the helicase activity of this enzyme is essential for its role in assembly of infectious WNV virions . Over-expression of the capsid-binding region of DDX56 also reduces infectivity of WNV suggesting that interaction of DDX56 and capsid protein is an important step in the virion assembly pathway . To our knowledge , this is the first study showing that enzymatic activity of a cellular helicase is critical for infectivity of flaviviruses . Crown\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Although flaviviruses encode their own helicases ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"evidence suggests that cellular helicases are also required for replication and/or assembly of these viruses .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"By and large , the mechanisms of action for viral and cellular helicases are not known .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Moreover , in some cases ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"enzymatic activity is not even required for their roles in virus biology .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Recently , we showed that expression of the host nucleolar helicase DDX56 is important for infectivity of West Nile virus ( WNV ) particles .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"In the present study , we demonstrate that the helicase activity of this enzyme is essential for its role in assembly of infectious WNV virions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Over-expression of the capsid-binding region of DDX56 also reduces infectivity of WNV suggesting that interaction of DDX56 and capsid protein is an important step in the virion assembly pathway .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"To our knowledge , this is the first study showing that enzymatic activity of a cellular helicase is critical for infectivity of flaviviruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Crown\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 10}]}"}]}
{"paper_id": "887dd9e6363c5a07dc9c13d38618c4e9bd3c372b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nYersinia pestis ( Y. pestis ) is the causative pathogen of plague , a highly fatal disease for which an effective vaccine , especially against mucosal transmission , is still not available . Like many bacterial infections , antigen-specific antibody responses have been traditionally considered critical , if not solely responsible , for vaccine-induced protection against Y. pestis . Studies in recent years have suggested the importance of T cell immune responses against Y. pestis infection but information is still limited about the details of Y. pestis antigen-specific T cell immune responses . In current report , studies are conducted to identify the presence of CD8 + T cell epitopes in LcrV protein , the leading antigen of plague vaccine development . Furthermore , depletion of CD8 + T cells in LcrV DNA vaccinated Balb/C mice led to reduced protection against lethal intranasal challenge of Y. pestis . These findings establish that an LcrV DNA vaccine is able to elicit CD8 + T cell immune responses against specific epitopes of this key plague antigen and that a CD8 + T cell immune response is involved in LcrV DNA vaccine-elicited protection . Future studies in plague vaccine development will need to examine if the presence of detectable T cell immune responses , in particular CD8 + T-cell immune responses , will enhance the protection against Y. pestis in higher animal species or humans .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Yersinia pestis ( Y. pestis ) is the causative pathogen of plague ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"a highly fatal disease for which an effective vaccine ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"especially against mucosal transmission , is still not available .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Like many bacterial infections , antigen-specific antibody responses have been traditionally considered critical ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"if not solely responsible , for vaccine-induced protection against Y. pestis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Studies in recent years have suggested the importance of T cell immune responses against Y. pestis infection but information is still limited about the details of Y. pestis antigen-specific T cell immune responses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"In current report , studies are conducted to identify the presence of CD8 + T cell epitopes in LcrV protein ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"the leading antigen of plague vaccine development .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"Furthermore , depletion of CD8 + T cells in LcrV DNA vaccinated Balb/C mice led to reduced protection against lethal intranasal challenge of Y. pestis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"These findings establish that an LcrV DNA vaccine is able to elicit CD8 + T cell immune responses against specific epitopes of this key plague antigen and that a CD8 + T cell immune response is involved in LcrV DNA vaccine-elicited protection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Future studies in plague vaccine development will need to examine if the presence of detectable T cell immune responses ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"in particular CD8 + T-cell immune responses ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"will enhance the protection against Y. pestis in higher animal species or humans .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "b0d841f7331c175952da753a086795a5287c61e0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nA mathematical model is developed to study the spread of the COVID-19 epidemics in France . Data from French Public Agency of Health are considered to calibrate the model . The spread of the epidemics strongly depends on confinement measures . The aim of the paper is to predict the evolution of the epidemics under various scenarios that could be taken to quit confinement . The spread of the disease and its re-emergence strongly depends on these scenarios .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"A mathematical model is developed to study the spread of the COVID-19 epidemics in France .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Data from French Public Agency of Health are considered to calibrate the model .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"The spread of the epidemics strongly depends on confinement measures .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The aim of the paper is to predict the evolution of the epidemics under various scenarios that could be taken to quit confinement .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"The spread of the disease and its re-emergence strongly depends on these scenarios .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}]}"}]}
{"paper_id": "8c3c81a8e2b68f7ad969f521933682573986f188", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nFerret coronaviruses ( FRCoVs ) exist as an enteric and a systemic pathotype , of which the latter is highly lethal to ferrets . To our knowledge , this study provides the first full genome sequence of a FRCoV , tentatively called FRCoV-NL-2010 , which was detected in 2010 in ferrets in The Netherlands . Phylogenetic analysis showed that FRCoV-NL-2010 is most closely related to mink CoV , forming a separate clade of mustelid alphacoronavirus that split off early from other alphacoronaviruses . Based on sequence homology of the complete genome , we propose that these mustelid coronaviruses may be assigned to a new species . Comparison of FRCoV-NL-2010 with the partially sequenced ferret systemic coronavirus MSU-1 and ferret enteric coronavirus MSU-2 revealed that recombination in the spike , 3c and envelope genes occurred between different FRCoVs . The GenBank/EMBL/DDBJ accession number for the full-length nucleotide sequence of FRCoV-NL-2010 is KM347965 . Two supplementary tables are available with the online Supplementary Material . 2180 000520 ã\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Ferret coronaviruses ( FRCoVs ) exist as an enteric and a systemic pathotype ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"of which the latter is highly lethal to ferrets .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"To our knowledge , this study provides the first full genome sequence of a FRCoV ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"tentatively called FRCoV-NL-2010 , which was detected in 2010 in ferrets in The Netherlands .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Phylogenetic analysis showed that FRCoV-NL-2010 is most closely related to mink CoV ,\", \"label\": \"background\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"forming a separate clade of mustelid alphacoronavirus that split off early from other alphacoronaviruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Based on sequence homology of the complete genome ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"we propose that these mustelid coronaviruses may be assigned to a new species .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Comparison of FRCoV-NL-2010 with the partially sequenced ferret systemic coronavirus MSU-1 and ferret enteric coronavirus MSU-2 revealed that recombination in the spike ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"3c and envelope genes occurred between different FRCoVs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The GenBank/EMBL/DDBJ accession number for the full-length nucleotide sequence of FRCoV-NL-2010 is KM347965 .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"Two supplementary tables are available with the online Supplementary Material .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"2180 000520 ã\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 13}]}"}]}
{"paper_id": "f66963a9155d44a7f734c0f1d30cab3371cd99fa", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSteroid-induced osteonecrosis of the femoral head ( SONFH ) is a disabling , aseptic and ischemic disease that develops following steroid therapy . The pathogenesis of SONFH is unclear , so the early diagnosis and treatment for this disease is yet to be established . The purpose of the present study was to identify potential biomarkers for SONFH . The differential expression of serum proteins from patients with SONFH and healthy volunteers was analyzed by the proteomics method . The protein samples were labeled and subjected to isoelectric focusing and two-dimensional gel electrophoresis . The resultant protein spots were matched and quantified by an imaging analysis system . The differentially-expressed protein spots were subjected to in-gel trypsin digestion followed by matrix-assisted laser desorption ionization time-of-flight mass spectrometry . Significantly lower levels of complement component 3 ( C3 ) , C4 , inter-α-trypsin inhibitor heavy chain H4 and α-2-macroglobulin were found in the serum of patients with SONFH . These proteins are reported to be actively involved in intravascular coagulation , apoptosis and reactive oxygen species imbalance , indicating that multiple pathological reactions occur in SONFH and these proteins may serve as potential biomarkers for the diagnosis of SONFH .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Steroid-induced osteonecrosis of the femoral head ( SONFH ) is a disabling ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"aseptic and ischemic disease that develops following steroid therapy .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"The pathogenesis of SONFH is unclear ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"so the early diagnosis and treatment for this disease is yet to be established .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"The purpose of the present study was to identify potential biomarkers for SONFH .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"The differential expression of serum proteins from patients with SONFH and healthy volunteers was analyzed by the proteomics method .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"The protein samples were labeled and subjected to isoelectric focusing and two-dimensional gel electrophoresis .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"The resultant protein spots were matched and quantified by an imaging analysis system .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The differentially-expressed protein spots were subjected to in-gel trypsin digestion followed by matrix-assisted laser desorption ionization time-of-flight mass spectrometry .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Significantly lower levels of complement component 3 ( C3 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"C4 , inter-α-trypsin inhibitor heavy chain H4 and α-2-macroglobulin were found in the serum of patients with SONFH .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"These proteins are reported to be actively involved in intravascular coagulation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"apoptosis and reactive oxygen species imbalance ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"indicating that multiple pathological reactions occur in SONFH and these proteins may serve as potential biomarkers for the diagnosis of SONFH .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "32da24606ad160166f08cf05349eaadd580ccff0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe human coronaviruses ( CoV ) include HCoV-229E , HCoV-OC43 , HCoV-NL63 , and HCoV-HKU1 , some of which have been known for decades . The severe acute respiratory syndrome ( SARS ) CoV briefly emerged into the human population but was controlled . In 2012 , another novel severely human pathogenic CoV-the Middle East Respiratory Syndrome ( MERS ) - CoV-was identified in the Kingdom of Saudi Arabia ; 80 % of over 2000 human cases have been recorded over five years . Targeted research remains key to developing control strategies for MERS-CoV , a cause of mild illness in its camel reservoir . A new therapeutic toolbox being developed in response to MERS is also teaching us more about how CoVs cause disease . Travel-related cases continue to challenge the world 's surveillance and response capabilities , and more data are needed to understand unexplained primary transmission . Signs of genetic change have been recorded , but it remains unclear whether there is any impact on clinical disease . How camels came to carry the virus remains academic to the control of MERS . To date , human-to-human transmission has been inefficient , but virus surveillance , characterisation , and reporting are key to responding to any future change . MERS-CoV is not currently a pandemic threat ; it is spread mainly with the aid of human habit and error .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The human coronaviruses ( CoV ) include HCoV-229E ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"HCoV-OC43 , HCoV-NL63 , and HCoV-HKU1 ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"some of which have been known for decades .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The severe acute respiratory syndrome ( SARS ) CoV briefly emerged into the human population but was controlled .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"In 2012 , another novel severely human pathogenic CoV-the Middle East Respiratory Syndrome ( MERS ) - CoV-was identified in the Kingdom of Saudi Arabia ; 80 % of over 2000 human cases have been recorded over five years .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Targeted research remains key to developing control strategies for MERS-CoV ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"a cause of mild illness in its camel reservoir .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"A new therapeutic toolbox being developed in response to MERS is also teaching us more about how CoVs cause disease .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"Travel-related cases continue to challenge the world 's surveillance and response capabilities ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"and more data are needed to understand unexplained primary transmission .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"Signs of genetic change have been recorded ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"but it remains unclear whether there is any impact on clinical disease .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"How camels came to carry the virus remains academic to the control of MERS .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 13}, {\"segment_text\": \"To date , human-to-human transmission has been inefficient ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"but virus surveillance , characterisation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"and reporting are key to responding to any future change .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"MERS-CoV is not currently a pandemic threat ; it is spread mainly with the aid of human habit and error .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "12a13e50f5ddc7864d33743dedebe6a69f8ea547", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe evolution of cats as a solitary species has pressured feline viruses to develop highly efficient transmission strategies , the ability to persist within the host for long periods of time and the aptitude to adapt to natural and vaccine-induced immunological pressures . These characteristics render feline viruses particularly dangerous in catteries , shelters and rescue homes , were cats from different backgrounds live in close proximity . The possibility to induce short-term resistance of newcomer cats to a broad variety of viruses could help prevent the dissemination of viruses both within and outside such facilities . Oligonucleotides ( ODN ) containing unmethylated cytosine phosphate guanosine ( CpG ) motifs stimulate innate immune responses in mammals . We have previously shown that ODN 2216 , a class A CpG ODN , promotes the expression by feline immune cells of potent antiviral molecules that increase resistance of feline fibroblastic and epithelial cell lines to five common feline viruses . With the aim to test the safety and extent of the biological effects of ODN 2216 in the domestic cat , we performed an initial in vivo experiment in which two cats were injected the molecule once subcutaneously and two additional cats received control treatments . No side effects to administration of ODN 2216 were observed . Moreover , this molecule induced the expression of the myxovirus resistance ( Mx ) gene , a marker for the instigation of innate antiviral processes , in blood as well as in oral , conjunctival and rectal mucosa cells , indicating systemic biological activity of the molecule with protective potential at viral entry sites . Mx mRNA levels were already elevated in blood 6 h post injection of ODN 2216 , reached peak levels within 24 h and returned to basal values by 96-192 h after administration of the molecule . Similar induction patterns were observed in all analyzed mucosal cells . Plasma collected from treated cats at regular intervals until 96-192 h could moreover induce Mx mRNA expression in fcwf-4 cells and increase resistance of these cells to feline calicivirus inoculation . Finally , Mx mRNA levels measured in blood correlated with the degree of viral inhibition that was induced by plasma from the same cat and the same experimental time point . Our results altogether underline the promising potential of ODN 2216 in promoting antiviral defense mechanisms and inducing temporary resistance to viral infections in vivo in the domestic cat .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The evolution of cats as a solitary species has pressured feline viruses to develop highly efficient transmission strategies ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"the ability to persist within the host for long periods of time and the aptitude to adapt to natural and vaccine-induced immunological pressures .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"These characteristics render feline viruses particularly dangerous in catteries ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"shelters and rescue homes , were cats from different backgrounds live in close proximity .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"The possibility to induce short-term resistance of newcomer cats to a broad variety of viruses could help prevent the dissemination of viruses both within and outside such facilities .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Oligonucleotides ( ODN ) containing unmethylated cytosine phosphate guanosine ( CpG ) motifs stimulate innate immune responses in mammals .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"We have previously shown that ODN 2216 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"a class A CpG ODN ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"promotes the expression by feline immune cells of potent antiviral molecules that increase resistance of feline fibroblastic and epithelial cell lines to five common feline viruses .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"With the aim to test the safety and extent of the biological effects of ODN 2216 in the domestic cat ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 10}, {\"segment_text\": \"we performed an initial in vivo experiment in which two cats were injected the molecule once subcutaneously and two additional cats received control treatments .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"No side effects to administration of ODN 2216 were observed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Moreover , this molecule induced the expression of the myxovirus resistance ( Mx ) gene ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"a marker for the instigation of innate antiviral processes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"in blood as well as in oral ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"conjunctival and rectal mucosa cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"indicating systemic biological activity of the molecule with protective potential at viral entry sites .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Mx mRNA levels were already elevated in blood 6 h post injection of ODN 2216 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"reached peak levels within 24 h and returned to basal values by 96-192 h after administration of the molecule .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Similar induction patterns were observed in all analyzed mucosal cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"Plasma collected from treated cats at regular intervals until 96-192 h could moreover induce Mx mRNA expression in fcwf-4 cells and increase resistance of these cells to feline calicivirus inoculation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"Finally , Mx mRNA levels measured in blood correlated with the degree of viral inhibition that was induced by plasma from the same cat and the same experimental time point .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"Our results altogether underline the promising potential of ODN 2216 in promoting antiviral defense mechanisms and inducing temporary resistance to viral infections in vivo in the domestic cat .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}]}"}]}
{"paper_id": "7274032555eb0d73921b324afa56ee4e9f8f459c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBats have been identified as a natural reservoir for an increasing number of emerging zoonotic viruses , such as Hendra virus , Nipah virus , Ebola virus , Marburg virus , rabies and other lyssaviruses . Recently , a large number of viruses closely related to members of the genus Coronavirus have been associated with severe acute respiratory syndrome ( SARS ) and detected in bat species . In this study , samples were collected from 106 live bats of seven different bat species from 27 different locations in Slovenia . Coronaviruses were detected by RT-PCR in 14 out of 36 horseshoe bat ( Rhinolophus hipposideros ) fecal samples , with 38.8 % virus prevalence . Sequence analysis of a 405-nucleotide region of the highly conserved RNA polymerase gene ( pol ) showed that all coronaviruses detected in this study are genetically closely related , with 99.5-100 % nucleotide identity , and belong to group 2 of the coronaviruses . The most closely related virus sequence in GenBank was SARS bat isolate Rp3/2004 ( DQ071615 ) within the SARS-like CoV cluster , sharing 85 % nucleotide identity and 95.6 % amino acid identity . The potential risk of a new group of bat coronaviruses as a reservoir for human infections is highly suspected , and further molecular epidemiologic studies of these bat coronaviruses are needed .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Bats have been identified as a natural reservoir for an increasing number of emerging zoonotic viruses ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"such as Hendra virus , Nipah virus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Ebola virus , Marburg virus , rabies and other lyssaviruses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Recently , a large number of viruses closely related to members of the genus Coronavirus have been associated with severe acute respiratory syndrome ( SARS ) and detected in bat species .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"In this study , samples were collected from 106 live bats of seven different bat species from 27 different locations in Slovenia .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Coronaviruses were detected by RT-PCR in 14 out of 36 horseshoe bat ( Rhinolophus hipposideros ) fecal samples ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"with 38.8 % virus prevalence .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Sequence analysis of a 405-nucleotide region of the highly conserved RNA polymerase gene ( pol ) showed that all coronaviruses detected in this study are genetically closely related ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"with 99.5-100 % nucleotide identity ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"and belong to group 2 of the coronaviruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The most closely related virus sequence in GenBank was SARS bat isolate Rp3/2004 ( DQ071615 ) within the SARS-like CoV cluster ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"sharing 85 % nucleotide identity and 95.6 % amino acid identity .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"The potential risk of a new group of bat coronaviruses as a reservoir for human infections is highly suspected ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"and further molecular epidemiologic studies of these bat coronaviruses are needed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "2e6263111a76ff0d43e7e3cde2692df04533e4f7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIt is well established that increasing age is associated with a decreased capacity of the immune system to mediate effective immune responses to vaccination and invading pathogens . Because of the inherent limitations of conducting experiments in humans , much of what we have learned is owed to the utility of experimental mouse models of aging . Recent studies performed in the mouse have demonstrated mechanisms responsible for age-related declines in the function of CD4 + and CD8 + cells . This review describes key findings regarding age-related defects in T-cell function and discusses the impact these defects have on vaccine efficacy and immunity .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"It is well established that increasing age is associated with a decreased capacity of the immune system to mediate effective immune responses to vaccination and invading pathogens .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Because of the inherent limitations of conducting experiments in humans ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"much of what we have learned is owed to the utility of experimental mouse models of aging .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Recent studies performed in the mouse have demonstrated mechanisms responsible for age-related declines in the function of CD4 + and CD8 + cells .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"This review describes key findings regarding age-related defects in T-cell function and discusses the impact these defects have on vaccine efficacy and immunity .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}]}"}]}
{"paper_id": "2654700a3429a7d7cd3f6c5e052edd175b7be5f8", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSevere inflammation may lead to multiple organs dysfunction syndrome , which has a high mortality . MicroRNA is found participated in this process . In this study we developed a lipopolysaccharide-induced inflammation cell model on macrophages and a lipopolysaccharide-induced inflammation mouse model . It was found that during inflammation , microRNA-9 was increased , accompanied with the up-regulation of pro-inflammatory cytokines and anti-inflammatory cytokines . Down-regulation of microRNA-9 inhibited the up-regulation of inflammatory cytokines , promoted the up-regulation of anti-inflammatory cytokines and induced the remission of organ damage , showing a protective effect in inflammation . Bioinformatics analysis combined with luciferase reporter assay showed that SIRT1 was the target gene of microRNA-9 . Transfection of microRNA-9 inhibitor could increase the level of SIRT1 and decrease the activation of NF-κB pathway in macrophages . Myeloid specific sirt1 knockout mice were included and we found that lack of SIRT1 in mice macrophages led to aggravated inflammation , cell apoptosis and organ injury , and eliminated the protective property of microRNA-9 inhibitor . In conclusion , we demonstrated that inhibition of microRNA-9 could alleviate inflammation through the up-regulation of SIRT1 and then suppressed the activation of NF-κB pathway . This is a meaningful explore about the specific mechanism of microRNA-9 in inflammation .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Severe inflammation may lead to multiple organs dysfunction syndrome ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"which has a high mortality .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"MicroRNA is found participated in this process .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"In this study we developed a lipopolysaccharide-induced inflammation cell model on macrophages and a lipopolysaccharide-induced inflammation mouse model .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"It was found that during inflammation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"microRNA-9 was increased , accompanied with the up-regulation of pro-inflammatory cytokines and anti-inflammatory cytokines .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Down-regulation of microRNA-9 inhibited the up-regulation of inflammatory cytokines ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"promoted the up-regulation of anti-inflammatory cytokines and induced the remission of organ damage ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"showing a protective effect in inflammation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Bioinformatics analysis combined with luciferase reporter assay showed that SIRT1 was the target gene of microRNA-9 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Transfection of microRNA-9 inhibitor could increase the level of SIRT1 and decrease the activation of NF-κB pathway in macrophages .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Myeloid specific sirt1 knockout mice were included and we found that lack of SIRT1 in mice macrophages led to aggravated inflammation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"cell apoptosis and organ injury ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"and eliminated the protective property of microRNA-9 inhibitor .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"In conclusion , we demonstrated that inhibition of microRNA-9 could alleviate inflammation through the up-regulation of SIRT1 and then suppressed the activation of NF-κB pathway .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"This is a meaningful explore about the specific mechanism of microRNA-9 in inflammation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "a21f8d21e09607e555468d0ed155126daaeb37cd", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAlthough antibodies against West Nile virus ( WNV ) have been detected in the sera of dromedaries in the Middle East , North Africa and Spain , no WNV has been isolated or amplified from dromedary or Bactrian camels . In this study , WNV was isolated from Vero cells inoculated with both nasal swab and pooled trachea/lung samples from a dromedary calf in Dubai . Completegenome sequencing and phylogenetic analysis using the near-whole-genome polyprotein revealed that the virus belonged to lineage 1a . There was no clustering of the present WNV with other WNVs isolated in other parts of the Middle East . Within lineage 1a , the dromedary WNV occupied a unique position , although it was most closely related to other WNVs of cluster 2 . Comparative analysis revealed that the putative E protein encoded by the genome possessed the original WNV E protein glycosylation motif NYS at E154-156 , which contained the N-linked glycosylation site at N-154 associated with increased WNV pathogenicity and neuroinvasiveness . In the putative NS1 protein , the A70S substitution observed in other cluster 2 WNVs and P250 , which has been implicated in neuroinvasiveness , were present . In addition , the foo motif in the putative NS2A protein , which has been implicated in neuroinvasiveness , was detected . Notably , the amino-acid residues at 14 positions in the present dromedary WNV genome differed from those in most of the closely related WNV strains in cluster 2 of lineage 1a , with the majority of these differences observed in the putative E and NS5 proteins . The present study is the first to demonstrate the isolation of WNV from dromedaries . This finding expands the possible reservoirs of WNV and sources of WNV infection .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Although antibodies against West Nile virus ( WNV ) have been detected in the sera of dromedaries in the Middle East ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"North Africa and Spain , no WNV has been isolated or amplified from dromedary or Bactrian camels .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"In this study , WNV was isolated from Vero cells inoculated with both nasal swab and pooled trachea/lung samples from a dromedary calf in Dubai .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Completegenome sequencing and phylogenetic analysis using the near-whole-genome polyprotein revealed that the virus belonged to lineage 1a .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"There was no clustering of the present WNV with other WNVs isolated in other parts of the Middle East .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Within lineage 1a , the dromedary WNV occupied a unique position ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"although it was most closely related to other WNVs of cluster 2 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Comparative analysis revealed that the putative E protein encoded by the genome possessed the original WNV E protein glycosylation motif NYS at E154-156 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"which contained the N-linked glycosylation site at N-154 associated with increased WNV pathogenicity and neuroinvasiveness .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"In the putative NS1 protein ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"the A70S substitution observed in other cluster 2 WNVs and P250 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"which has been implicated in neuroinvasiveness , were present .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"In addition , the foo motif in the putative NS2A protein ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"which has been implicated in neuroinvasiveness , was detected .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Notably , the amino-acid residues at 14 positions in the present dromedary WNV genome differed from those in most of the closely related WNV strains in cluster 2 of lineage 1a ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"with the majority of these differences observed in the putative E and NS5 proteins .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"The present study is the first to demonstrate the isolation of WNV from dromedaries .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"This finding expands the possible reservoirs of WNV and sources of WNV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "9ea1a900f1243ce3264700e9eec29b402892674c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAdenovirus is one of the most common causes of viral acute respiratory infections . To identify the types of human adenoviruses ( HAdVs ) causing respiratory illness in Beijing , a sentinel surveillance project on the viral aetiology of acute respiratory infection was initiated in 2011 . Through the surveillance project , 4617 cases of respiratory infections were identified during 2011-2013 . Throat swabs ( pharynx and tonsil secretions ) were collected from all the patients , and 15 different respiratory viruses were screened by multiplex one-step PCR method . 45 were identified as adenovirus-positive from sporadic and outbreak cases of respiratory infection by a multiplex one-step RT-PCR method , and a total of 21 adenovirus isolates were obtained . Five HAdV types among three species , including HAdV-3 ( species HAdV-B ) , HAdV-4 ( species HAdV-E ) , HAdV-7 ( species HAdV-B ) , HAdV-55 ( species HAdV-B ) , and an undefined HAdV type ( species HAdV-C ) were identified . The comparison results of the penton base , hexon , and fiber gene sequences of the Beijing HAdV-3 , HAdV-4 , HAdV-7 , and HAdV-55 strains in this study and those from the GenBank database indicated significant spatial and temporal conservation and stability of sequences within the genome ; however , the phylogenetic relationship indicated that both strain BJ04 and strain BJ09 isolated in 2012 and 2013 , respectively , may have recombined between HAdV-1 genome and HAdV-2 genome within species HAdV-C , indicating intraspecies recombination . This study confirmed that at least 5 HAdV types including HAdV-3 , HAdV-4 , HAdV-7 , HAdV-55 and an undefined HAdV type were co-circulating and were the causative agents of respiratory tract infections in recent years in Beijing . HAdV-3 , HAdV-4 , HAdV-7 , and HAdV-55 showed the apparent stability of the genomes , while intraspecies recombination was identified in strain BJ04 and BJ09 . The recombinants carrying penton base gene of HAdV-1 as well as hexon and fiber genes of HAdV-2 might be a novel type of HAdV worthy of further study . Adenoviruses in Beijing during 2011 PLOS ONE |\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Adenovirus is one of the most common causes of viral acute respiratory infections .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"To identify the types of human adenoviruses ( HAdVs ) causing respiratory illness in Beijing ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"a sentinel surveillance project on the viral aetiology of acute respiratory infection was initiated in 2011 .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"Through the surveillance project , 4617 cases of respiratory infections were identified during 2011-2013 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Throat swabs ( pharynx and tonsil secretions ) were collected from all the patients ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"and 15 different respiratory viruses were screened by multiplex one-step PCR method .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"45 were identified as adenovirus-positive from sporadic and outbreak cases of respiratory infection by a multiplex one-step RT-PCR method ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"and a total of 21 adenovirus isolates were obtained .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Five HAdV types among three species ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"including HAdV-3 ( species HAdV-B ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"HAdV-4 ( species HAdV-E ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"HAdV-7 ( species HAdV-B ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"HAdV-55 ( species HAdV-B ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"and an undefined HAdV type ( species HAdV-C ) were identified .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"The comparison results of the penton base ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"hexon , and fiber gene sequences of the Beijing HAdV-3 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"HAdV-4 , HAdV-7 , and HAdV-55 strains in this study and those from the GenBank database indicated significant spatial and temporal conservation and stability of sequences within the genome ; however ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"the phylogenetic relationship indicated that both strain BJ04 and strain BJ09 isolated in 2012 and 2013 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"respectively , may have recombined between HAdV-1 genome and HAdV-2 genome within species HAdV-C , indicating intraspecies recombination .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"This study confirmed that at least 5 HAdV types including HAdV-3 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}, {\"segment_text\": \"HAdV-4 , HAdV-7 , HAdV-55 and an undefined HAdV type were co-circulating and were the causative agents of respiratory tract infections in recent years in Beijing .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}, {\"segment_text\": \"HAdV-3 , HAdV-4 , HAdV-7 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 22}, {\"segment_text\": \"and HAdV-55 showed the apparent stability of the genomes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 23}, {\"segment_text\": \"while intraspecies recombination was identified in strain BJ04 and BJ09 .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 24}, {\"segment_text\": \"The recombinants carrying penton base gene of HAdV-1 as well as hexon and fiber genes of HAdV-2 might be a novel type of HAdV worthy of further study .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 25}, {\"segment_text\": \"Adenoviruses in Beijing during 2011 PLOS ONE |\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 26}]}"}]}
{"paper_id": "7f69a764a32e9fefc971d79582da33db151cdeb5", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCellular membranes are continuously remodeled . The crescent-shaped bin-amphiphysin-rvs ( BAR ) domains remodel membranes in multiple cellular pathways . Based on studies of isolated BAR domains in vitro , the current paradigm is that BAR domain-containing proteins polymerize into cylindrical scaffolds that stabilize lipid tubules . But in nature , proteins that contain BAR domains often also contain large intrinsically disordered regions . Using in vitro and live cell assays , here we show that full-length BAR domain-containing proteins , rather than stabilizing membrane tubules , are instead surprisingly potent drivers of membrane fission . Specifically , when BAR scaffolds assemble at membrane surfaces , their bulky disordered domains become crowded , generating steric pressure that destabilizes lipid tubules . More broadly , we observe this behavior with BAR domains that have a range of curvatures . These data suggest that the ability to concentrate disordered domains is a key driver of membrane remodeling and fission by BAR domain-containing proteins .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Cellular membranes are continuously remodeled .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The crescent-shaped bin-amphiphysin-rvs ( BAR ) domains remodel membranes in multiple cellular pathways .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Based on studies of isolated BAR domains in vitro ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"the current paradigm is that BAR domain-containing proteins polymerize into cylindrical scaffolds that stabilize lipid tubules .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"But in nature , proteins that contain BAR domains often also contain large intrinsically disordered regions .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Using in vitro and live cell assays ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"here we show that full-length BAR domain-containing proteins ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"rather than stabilizing membrane tubules ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"are instead surprisingly potent drivers of membrane fission .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Specifically , when BAR scaffolds assemble at membrane surfaces ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"their bulky disordered domains become crowded ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"generating steric pressure that destabilizes lipid tubules .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"More broadly , we observe this behavior with BAR domains that have a range of curvatures .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"These data suggest that the ability to concentrate disordered domains is a key driver of membrane remodeling and fission by BAR domain-containing proteins .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "4f22ff2c7ce145ff907bcd3d5fd71ae8d9083492", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe safety and the efficacy of a modified-live ( ML ) canine coronavirus ( CCoV ) vaccine strain 257/98 - 3c was evaluated in 14 dogs seronegative and virus negative for CCoV . For the safety test , four dogs were inoculated , two by intramuscular and two by oronasal route , with 10 times the vaccinal dose . During the observation period ( 28 days ) all dogs did not display any local or systemic reaction . For the efficacy test , eight dogs were vaccinated by intramuscular ( four dogs-group A ) or by oronasal route ( four dogs-group B ) . Two dogs were maintained as non-vaccinated controls . In the dogs of group A , vaccinal virus was not detected in faecal samples by virus isolation ( VI ) and by PCR assay , while in the dogs of group B , the virus was revealed for six median days only by PCR . Twenty-eight days later , the vaccinated and control dogs were challenged with a field CCoV strain . After the challenge , the vaccinated dogs did not display clinical signs and the dogs of group A shed virus for 5.5 median days , evaluated by VI , and for 10 median days evaluated by PCR . Virus shedding was not observed , both by VI and PCR assay , in the dogs of group B . The two control dogs displayed moderate clinical signs and the virus was detected by VI for 14.5 median days starting from day 3 post-challenge ( dpc 3 ) and by PCR assay for 23 median days starting from dpc 1 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The safety and the efficacy of a modified-live ( ML ) canine coronavirus ( CCoV ) vaccine strain 257/98 - 3c was evaluated in 14 dogs seronegative and virus negative for CCoV .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"For the safety test , four dogs were inoculated ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"two by intramuscular and two by oronasal route ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"with 10 times the vaccinal dose .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"During the observation period ( 28 days ) all dogs did not display any local or systemic reaction .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"For the efficacy test , eight dogs were vaccinated by intramuscular ( four dogs-group A ) or by oronasal route ( four dogs-group B ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Two dogs were maintained as non-vaccinated controls .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"In the dogs of group A ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"vaccinal virus was not detected in faecal samples by virus isolation ( VI ) and by PCR assay ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"while in the dogs of group B ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"the virus was revealed for six median days only by PCR .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Twenty-eight days later , the vaccinated and control dogs were challenged with a field CCoV strain .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"After the challenge , the vaccinated dogs did not display clinical signs and the dogs of group A shed virus for 5.5 median days ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"evaluated by VI , and for 10 median days evaluated by PCR .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Virus shedding was not observed ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"both by VI and PCR assay ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"in the dogs of group B .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"The two control dogs displayed moderate clinical signs and the virus was detected by VI for 14.5 median days starting from day 3 post-challenge ( dpc 3 ) and by PCR assay for 23 median days starting from dpc 1 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "82012173f8bddbcaa3138ccc3aae2d554e1dcd1f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAcute respiratory infections ( ARI ) are a major cause of morbidity worldwide . 1 Some of the earliest studies to describe the epidemiology of these infections were household cohort studies . ( 2 ) ( 3 ) ( 4 ) ( 5 ) ( 6 ) ( 7 ) The largest of these were conducted in Seattle , Washington and Tecumseh , Michigan in the 1960s and 1970s 6,7 and they provided information on the relative frequency , seasonality and symptomatic characteristics of ARI shortly after many respiratory viruses were first identified . 7 Given that the role of household structure in seasonal incidence and transmission of respiratory viruses was the primary objective , an individual 's longitudinal history of infection was not a major focus . Indeed , during the first phase of the Tecumseh Study of Respiratory Illness , households were maintained on report for only 1 year , and then gradually replaced so that the entire community could be represented over time . 8 These historical studies relied on cell culture for virus identification , a method that requires specimens to be processed quickly and is considerably less sensitive than current molecular methods . 9 For this reason , the Tecumseh study and others relied extensively on serodiagnosis of influenza infection using twice yearly blood specimens . 10 It was not possible to time infections in those who only were serologically positive , limiting the ability to do robust analyses of transmission patterns . 11 With current molecular techniques , it has become much easier to identify a broad range of agents of respiratory infection . This allows documentation of infection , co-infection and subsequent re-infection . Collecting specimens within a short time from the onset of symptoms still maximizes the likelihood of accurate and timely identification of viruses associated with a respiratory illness for studies of transmission and vaccine effectiveness . Collection of regular blood specimens continues to be valuable as well , for both virus identification and for analysis of serologic correlates of protection . The Household Influenza Vaccine Evaluation ( HIVE ) Study is an ongoing prospective household cohort study that began in 2010 . The HIVE Study was based on the original Tecumseh Study of Respiratory Illness 6 with several key modifications to illness surveillance and to laboratory methods for identification of respiratory viruses . While respiratory virus infections in general could be studied , the primary objective was to estimate the effectiveness of influenza vaccines using a cohort design for comparison with studies using the testnegative design ( TND ) . Under the TND , specimens are collected from participants who meet a respiratory illness case V C The Author ( s )\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Acute respiratory infections ( ARI ) are a major cause of morbidity worldwide .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"1 Some of the earliest studies to describe the epidemiology of these infections were household cohort studies .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"( 2 ) ( 3 ) ( 4 ) ( 5 ) ( 6 ) ( 7 ) The largest of these were conducted in Seattle ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Washington and Tecumseh , Michigan in the 1960s and 1970s 6,7 and they provided information on the relative frequency ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"seasonality and symptomatic characteristics of ARI shortly after many respiratory viruses were first identified .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"7 Given that the role of household structure in seasonal incidence and transmission of respiratory viruses was the primary objective ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"an individual 's longitudinal history of infection was not a major focus .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Indeed , during the first phase of the Tecumseh Study of Respiratory Illness ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"households were maintained on report for only 1 year ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"and then gradually replaced so that the entire community could be represented over time .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"8 These historical studies relied on cell culture for virus identification ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"a method that requires specimens to be processed quickly and is considerably less sensitive than current molecular methods .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"9 For this reason , the Tecumseh study and others relied extensively on serodiagnosis of influenza infection using twice yearly blood specimens .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}, {\"segment_text\": \"10 It was not possible to time infections in those who only were serologically positive ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 14}, {\"segment_text\": \"limiting the ability to do robust analyses of transmission patterns .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 15}, {\"segment_text\": \"11 With current molecular techniques ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 16}, {\"segment_text\": \"it has become much easier to identify a broad range of agents of respiratory infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 17}, {\"segment_text\": \"This allows documentation of infection , co-infection and subsequent re-infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 18}, {\"segment_text\": \"Collecting specimens within a short time from the onset of symptoms still maximizes the likelihood of accurate and timely identification of viruses associated with a respiratory illness for studies of transmission and vaccine effectiveness .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 19}, {\"segment_text\": \"Collection of regular blood specimens continues to be valuable as well ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 20}, {\"segment_text\": \"for both virus identification and for analysis of serologic correlates of protection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 21}, {\"segment_text\": \"The Household Influenza Vaccine Evaluation ( HIVE ) Study is an ongoing prospective household cohort study that began in 2010 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 22}, {\"segment_text\": \"The HIVE Study was based on the original Tecumseh Study of Respiratory Illness 6 with several key modifications to illness surveillance and to laboratory methods for identification of respiratory viruses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 23}, {\"segment_text\": \"While respiratory virus infections in general could be studied ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}, {\"segment_text\": \"the primary objective was to estimate the effectiveness of influenza vaccines using a cohort design for comparison with studies using the testnegative design ( TND ) .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 25}, {\"segment_text\": \"Under the TND , specimens are collected from participants who meet a respiratory illness case V C The Author ( s )\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 26}]}"}]}
{"paper_id": "aa7fca3d5bcd3cf20701f65e94403fcd66159f2b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIntensive observations , analysis and modeling within the framework of the rangelands atmosphere-hydrosphere-biosphere interaction study experiment in northeastern Asia ( RAISE ) project , have allowed investigations into the hydrologic cycle in the ecotone of forest-steppe , and its relation to atmosphere and ecosystem in the eastern part of Mongolia . In this region , changes in the climate have been reported and a market oriented economy was introduced recently , but their impact on the natural environment is still not well understood . In this RAISE special issue , the outcome is presented of the studies carried out by six groups within RAISE , namely : ( 1 ) Land-atmosphere interaction analysis , ( 2 ) ecosystem analysis and modeling , ( 3 ) hydrologic cycle analysis , ( 4 ) climatic modeling , ( 5 ) hydrologic modeling , and ( 6 ) integration . The results are organized in five relevant categories comprising ( i ) hydrologic cycle including precipitation , groundwater , and surface water , ( ii ) hydrologic cycle and ecosystem , ( iii ) surface-atmosphere interaction , ( iv ) effect of grazing activities on soils , plant ecosystem and surface fluxes , and ( v ) 0022-1694 / $ - see front matter ª a v a i l a b l e a t w w w . s c i e n c e d i r e c t . c o m j o u r n a l h o m e p a g e : w w w . e l s e v i e r . c o m / l o c a t e / j h y d r o l future prediction . Comparison with studies on rangelands in other parts of the world , and some future directions of studies still needed in this region are also summarized . ª 2006 Elsevier B.V. All rights reserved . An overview of the rangelands atmosphere-hydrosphere-biosphere interaction\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Intensive observations , analysis and modeling within the framework of the rangelands atmosphere-hydrosphere-biosphere interaction study experiment in northeastern Asia ( RAISE ) project ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"have allowed investigations into the hydrologic cycle in the ecotone of forest-steppe ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"and its relation to atmosphere and ecosystem in the eastern part of Mongolia .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"In this region , changes in the climate have been reported and a market oriented economy was introduced recently ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"but their impact on the natural environment is still not well understood .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"In this RAISE special issue ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"the outcome is presented of the studies carried out by six groups within RAISE ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"namely : ( 1 ) Land-atmosphere interaction analysis ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"( 2 ) ecosystem analysis and modeling ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"( 3 ) hydrologic cycle analysis ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"( 4 ) climatic modeling ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"( 5 ) hydrologic modeling ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"and ( 6 ) integration .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}, {\"segment_text\": \"The results are organized in five relevant categories comprising ( i ) hydrologic cycle including precipitation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"groundwater , and surface water ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"( ii ) hydrologic cycle and ecosystem ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"( iii ) surface-atmosphere interaction ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"( iv ) effect of grazing activities on soils ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"plant ecosystem and surface fluxes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"and ( v ) 0022-1694 / $ - see front matter ª a v a i l a b l e a t w w w .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}, {\"segment_text\": \"s c i e n c e d i r e c t .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 21}, {\"segment_text\": \"c o m j o u r n a l h o m e p a g e : w w w .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 22}, {\"segment_text\": \"e l s e v i e r .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 23}, {\"segment_text\": \"c o m / l o c a t e / j h y d r o l future prediction .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 24}, {\"segment_text\": \"Comparison with studies on rangelands in other parts of the world ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 25}, {\"segment_text\": \"and some future directions of studies still needed in this region are also summarized .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 26}, {\"segment_text\": \"ª 2006 Elsevier B.V. All rights reserved .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 27}, {\"segment_text\": \"An overview of the rangelands atmosphere-hydrosphere-biosphere interaction\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 28}]}"}]}
{"paper_id": "798026310eaadd09df393473a730d6935f91b4d4", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPhenomenon of unequal use of synonymous codons in Mycobacterium tuberculosis is common . Codon usage bias not only plays an important regulatory role at the level of gene expression , but also helps in improving the accuracy and efficiency of translation . Meanwhile , codon usage pattern of Mycobacterium tuberculosis genome is important for interpreting evolutionary characteristics in species . In order to investigate the codon usage pattern of the Mycobacterium tuberculosis genome , 12 Mycobacterium tuberculosis genomes from different area are downloaded from the GeneBank . The correlations between G 3 , GC 12 , whole GC content , codon adaptation index , codon bias index , and so on of Mycobacterium tuberculosis genomes are calculated . The ENC-plot , relationship between A 3 / ( A 3 + T 3 ) and G 3 / ( G 3 + C 3 ) , GC 12 versus GC 3 plot , and the RSCU of overall/separated genomes all show that the codon usage bias exists in all 12 Mycobacterium tuberculosis genomes . Lastly , relationship between CBI and the equalization of ENC shows a strong negative correlation between them . The relationship between protein length and GC content ( GC 3 and GC 12 ) shows that more obvious differences in the GC content may be in shorter protein . These results show that codon usage bias existing in the Mycobacterium tuberculosis genomes could be used for further study on their evolutionary phenomenon .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Phenomenon of unequal use of synonymous codons in Mycobacterium tuberculosis is common .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Codon usage bias not only plays an important regulatory role at the level of gene expression ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"but also helps in improving the accuracy and efficiency of translation .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Meanwhile , codon usage pattern of Mycobacterium tuberculosis genome is important for interpreting evolutionary characteristics in species .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"In order to investigate the codon usage pattern of the Mycobacterium tuberculosis genome ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"12 Mycobacterium tuberculosis genomes from different area are downloaded from the GeneBank .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"The correlations between G 3 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"GC 12 , whole GC content ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"codon adaptation index , codon bias index ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"and so on of Mycobacterium tuberculosis genomes are calculated .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"The ENC-plot , relationship between A 3 / ( A 3 + T 3 ) and G 3 / ( G 3 + C 3 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"GC 12 versus GC 3 plot ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"and the RSCU of overall/separated genomes all show that the codon usage bias exists in all 12 Mycobacterium tuberculosis genomes .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"Lastly , relationship between CBI and the equalization of ENC shows a strong negative correlation between them .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"The relationship between protein length and GC content ( GC 3 and GC 12 ) shows that more obvious differences in the GC content may be in shorter protein .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"These results show that codon usage bias existing in the Mycobacterium tuberculosis genomes could be used for further study on their evolutionary phenomenon .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "2822c9550311df8e6325df17b17cfde48c9ab6ab", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nWe created an immunosensing platform for the detection of proteins in a buffer solution . Our sensing platform relies on graphene oxide ( GO ) nanosheets conjugated with antibodies to provide quantitative binding sites for analyte proteins . When analyte proteins and standard fluorescein-labelled proteins are competing for the binding sites , the assay exhibits quantitative fluorescence quenching by GO for the fluorescein-labelled proteins as determined by the analyte protein concentration . Because of this mechanism , measured fluorescence intensity from unquenched fluorescein-labelled protein was shown to increase with an increasing analyte protein concentration . As an alternative to the conventional enzyme-linked immunosorbent assay ( ELISA ) , our method does not require an enzyme-linked second antibody for protein recognition and the enzyme for optical signal measurement . Thus , it is beneficial with its low cost and fewer systematic errors caused by the series of antigen-antibody recognition steps in ELISA . Immune globulin G ( IgG ) was introduced as a model protein to test our method and our results showed that the limit of detection for IgG was 4.67 pmol mL − 1 in the buffer solution . This sensing mechanism could be developed into a promising biosensor for the detection of proteins , which would broaden the spectrum of GO applications in both analytical biochemistry and clinical diagnosis .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"We created an immunosensing platform for the detection of proteins in a buffer solution .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Our sensing platform relies on graphene oxide ( GO ) nanosheets conjugated with antibodies to provide quantitative binding sites for analyte proteins .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"When analyte proteins and standard fluorescein-labelled proteins are competing for the binding sites ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"the assay exhibits quantitative fluorescence quenching by GO for the fluorescein-labelled proteins as determined by the analyte protein concentration .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Because of this mechanism , measured fluorescence intensity from unquenched fluorescein-labelled protein was shown to increase with an increasing analyte protein concentration .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"As an alternative to the conventional enzyme-linked immunosorbent assay ( ELISA ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"our method does not require an enzyme-linked second antibody for protein recognition and the enzyme for optical signal measurement .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Thus , it is beneficial with its low cost and fewer systematic errors caused by the series of antigen-antibody recognition steps in ELISA .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Immune globulin G ( IgG ) was introduced as a model protein to test our method and our results showed that the limit of detection for IgG was 4.67 pmol mL − 1 in the buffer solution .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"This sensing mechanism could be developed into a promising biosensor for the detection of proteins ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"which would broaden the spectrum of GO applications in both analytical biochemistry and clinical diagnosis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}]}"}]}
{"paper_id": "e92488019ca299d19beabb885c7c71b12b535712", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCoronaviruses ( CoVs ) are important human and animal pathogens that induce fatal respiratory , gastrointestinal and neurological disease . The outbreak of the severe acute respiratory syndrome ( SARS ) in 2002/2003 has demonstrated human vulnerability to ( Coronavirus ) CoV epidemics . Neither vaccines nor therapeutics are available against human and animal CoVs . Knowledge of host cell proteins that take part in pivotal virus-host interactions could define broad-spectrum antiviral targets . In this study , we used a systems biology approach employing a genome-wide yeast-two hybrid interaction screen to identify immunopilins ( PPIA , PPIB , PPIH , PPIG , FKBP1A , FKBP1B ) as interaction partners of the CoV non-structural protein 1 ( Nsp1 ) . These molecules modulate the Calcineurin/NFAT pathway that plays an important role in immune cell activation . Overexpression of NSP1 and infection with live SARS-CoV strongly increased signalling through the Calcineurin/NFAT pathway and enhanced the induction of interleukin 2 , compatible with late-stage immunopathogenicity and long-term cytokine dysregulation as observed in severe SARS cases . Conversely , inhibition of cyclophilins by cyclosporine A ( CspA ) blocked the replication of CoVs of all genera , including SARS-CoV , human CoV-229E and - NL-63 , feline CoV , as well as avian infectious bronchitis virus . Non-immunosuppressive derivatives of CspA might serve as broad-range CoV inhibitors applicable against emerging CoVs as well as ubiquitous pathogens of humans and livestock . Citation : Pfefferle S , Schö pf J , Kö gl M , Friedel CC , Mü ller MA , et al. ( 2011 ) The SARS-Coronavirus-Host Interactome : Identification of Cyclophilins as Target for Pan-Coronavirus Inhibitors . PLoS Pathog 7 ( 10 ) : e1002331 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Coronaviruses ( CoVs ) are important human and animal pathogens that induce fatal respiratory , gastrointestinal and neurological disease .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The outbreak of the severe acute respiratory syndrome ( SARS ) in 2002/2003 has demonstrated human vulnerability to ( Coronavirus ) CoV epidemics .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Neither vaccines nor therapeutics are available against human and animal CoVs .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Knowledge of host cell proteins that take part in pivotal virus-host interactions could define broad-spectrum antiviral targets .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"In this study , we used a systems biology approach employing a genome-wide yeast-two hybrid interaction screen to identify immunopilins ( PPIA , PPIB , PPIH , PPIG , FKBP1A , FKBP1B ) as interaction partners of the CoV non-structural protein 1 ( Nsp1 ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"These molecules modulate the Calcineurin/NFAT pathway that plays an important role in immune cell activation .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"Overexpression of NSP1 and infection with live SARS-CoV strongly increased signalling through the Calcineurin/NFAT pathway and enhanced the induction of interleukin 2 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"compatible with late-stage immunopathogenicity and long-term cytokine dysregulation as observed in severe SARS cases .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"Conversely , inhibition of cyclophilins by cyclosporine A ( CspA ) blocked the replication of CoVs of all genera ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"including SARS-CoV , human CoV-229E and - NL-63 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"feline CoV , as well as avian infectious bronchitis virus .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"Non-immunosuppressive derivatives of CspA might serve as broad-range CoV inhibitors applicable against emerging CoVs as well as ubiquitous pathogens of humans and livestock .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"Citation : Pfefferle S , Schö pf J ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 13}, {\"segment_text\": \"Kö gl M , Friedel CC ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 14}, {\"segment_text\": \"Mü ller MA , et al. ( 2011 ) The SARS-Coronavirus-Host Interactome : Identification of Cyclophilins as Target for Pan-Coronavirus Inhibitors .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 15}, {\"segment_text\": \"PLoS Pathog 7 ( 10 ) : e1002331 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 16}]}"}]}
{"paper_id": "e00ab1ff9e72c8cdbccf3842b571eec260355675", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSince the first report of a viral disease associated with plants , the fascinating field of virology has evolved and aided mankind altogether . Viral infections are known for inflicting colossal economic losses worldwide in food/work/companion animals . During the last few decades\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Since the first report of a viral disease associated with plants ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"the fascinating field of virology has evolved and aided mankind altogether .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Viral infections are known for inflicting colossal economic losses worldwide in food/work/companion animals .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"During the last few decades\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}]}"}]}
{"paper_id": "fc0265a781a3609ee9c884fe0e2df2aeec57b0ea", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Pneumonia is a leading cause of morbidity and mortality in children worldwide ; however , its diagnosis can be challenging , especially in settings where skilled clinicians or standard imaging are unavailable . We sought to determine the diagnostic accuracy of lung ultrasound when compared to radiographically-confirmed clinical pediatric pneumonia . Methods : Between January 2012 and September 2013 , we consecutively enrolled children aged 2e59 months with primary respiratory complaints at the outpatient clinics , emergency department , and inpatient wards of the Instituto Nacional de Salud del Niño in Lima , Peru . All participants underwent clinical evaluation by a pediatrician and lung ultrasonography by one of three general practitioners . We also consecutively enrolled children without respiratory symptoms . Children with respiratory symptoms had a chest radiograph . We obtained ancillary laboratory testing in a subset . Results : Final clinical diagnoses included 453 children with pneumonia , 133 with asthma , 103 with bronchiolitis , and 143 with upper respiratory infections . In total , CXR confirmed the diagnosis in 191 ( 42 % ) of 453 children with clinical pneumonia . A consolidation on lung ultrasound , which is our primary endpoint for pneumonia , had a sensitivity of 88.5 % , specificity of 100 % , and an area under-the-curve of 0.94 ( 95 % CI 0.92 e0 .97 ) when compared to radiographically-confirmed clinical pneumonia . When any abnormality on lung ultrasound was compared to radiographically-confirmed clinical pneumonia the sensitivity increased to 92.2 % and the specificity decreased to 95.2 % , with an area under-the-curve of 0.94 ( 95 % CI 0.91 e0 .96 ) . Conclusions : Lung ultrasound had high diagnostic accuracy for the diagnosis of radiographicallyconfirmed pneumonia . Added benefits of lung ultrasound include rapid testing and high inter-rater agreement . Lung ultrasound may serve as an alternative tool for the diagnosis of pediatric pneumonia .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Pneumonia is a leading cause of morbidity and mortality in children worldwide ; however ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"its diagnosis can be challenging ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"especially in settings where skilled clinicians or standard imaging are unavailable .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"We sought to determine the diagnostic accuracy of lung ultrasound when compared to radiographically-confirmed clinical pediatric pneumonia .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Methods : Between January 2012 and September 2013 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"we consecutively enrolled children aged 2e59 months with primary respiratory complaints at the outpatient clinics ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"emergency department , and inpatient wards of the Instituto Nacional de Salud del Niño in Lima , Peru .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"All participants underwent clinical evaluation by a pediatrician and lung ultrasonography by one of three general practitioners .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"We also consecutively enrolled children without respiratory symptoms .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Children with respiratory symptoms had a chest radiograph .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"We obtained ancillary laboratory testing in a subset .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Results : Final clinical diagnoses included 453 children with pneumonia ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"133 with asthma , 103 with bronchiolitis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"and 143 with upper respiratory infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"In total , CXR confirmed the diagnosis in 191 ( 42 % ) of 453 children with clinical pneumonia .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"A consolidation on lung ultrasound ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"which is our primary endpoint for pneumonia ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"had a sensitivity of 88.5 % ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"specificity of 100 % , and an area under-the-curve of 0.94 ( 95 % CI 0.92 e0 .97 ) when compared to radiographically-confirmed clinical pneumonia .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"When any abnormality on lung ultrasound was compared to radiographically-confirmed clinical pneumonia the sensitivity increased to 92.2 % and the specificity decreased to 95.2 % ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}, {\"segment_text\": \"with an area under-the-curve of 0.94 ( 95 % CI 0.91 e0 .96 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}, {\"segment_text\": \"Conclusions : Lung ultrasound had high diagnostic accuracy for the diagnosis of radiographicallyconfirmed pneumonia .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"Added benefits of lung ultrasound include rapid testing and high inter-rater agreement .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"Lung ultrasound may serve as an alternative tool for the diagnosis of pediatric pneumonia .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}]}"}]}
{"paper_id": "d74ca96879ef6d9982cb7ddaf5396940697dc8dc", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nEbola virus and Marburg virus are members of the family of Filoviridae and are etiological agents of a deadly hemorrhagic fever disease . The clinical symptoms of Ebola and Marburg hemorrhagic fevers are difficult to distinguish and there are currently no specific antiviral therapies against either of the viruses . Therefore , a drug that is safe and effective against both would be an enormous breakthrough . We and others have shown that the folding of the glycoproteins of many enveloped viruses , including the filoviruses , is far more dependent upon the calnexin pathway of protein folding than are most host glycoproteins . Drugs that inhibit this pathway would be expected to be selectively antiviral . Indeed , as we summarize in this review , imino sugars that are competitive inhibitors of the host endoplasmic reticular a-glucosidases I and II , which are enzymes that process N-glycan on nascent glycoproteins and thereby inhibit calnexin binding to the nascent glycoproteins , have been shown to have antiviral activity against a number of enveloped viruses including filoviruses . In this review , we describe the state of development of imino sugars for use against the filoviruses , and provide an explanation for the basis of their antiviral activity as well as limitations .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Ebola virus and Marburg virus are members of the family of Filoviridae and are etiological agents of a deadly hemorrhagic fever disease .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The clinical symptoms of Ebola and Marburg hemorrhagic fevers are difficult to distinguish and there are currently no specific antiviral therapies against either of the viruses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Therefore , a drug that is safe and effective against both would be an enormous breakthrough .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"We and others have shown that the folding of the glycoproteins of many enveloped viruses ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"including the filoviruses , is far more dependent upon the calnexin pathway of protein folding than are most host glycoproteins .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Drugs that inhibit this pathway would be expected to be selectively antiviral .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"Indeed , as we summarize in this review ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"imino sugars that are competitive inhibitors of the host endoplasmic reticular a-glucosidases I and II ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"which are enzymes that process N-glycan on nascent glycoproteins and thereby inhibit calnexin binding to the nascent glycoproteins ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"have been shown to have antiviral activity against a number of enveloped viruses including filoviruses .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"In this review , we describe the state of development of imino sugars for use against the filoviruses ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 11}, {\"segment_text\": \"and provide an explanation for the basis of their antiviral activity as well as limitations .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}]}"}]}
{"paper_id": "96602c07c439a97e001abcd2e9c85fda998d64c6", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nTypically not assisted by proofreading , the RNAdependent RNA polymerases ( RdRPs ) encoded by the RNA viruses may need to independently control its fidelity to fulfill virus viability and fitness . However , the precise mechanism by which the RdRP maintains its optimal fidelity level remains largely elusive . By solving 2.1-2.5 Å resolution crystal structures of the classical swine fever virus ( CSFV ) NS5B , an RdRP with a unique naturally fused N-terminal domain ( NTD ) , we identified high-resolution intramolecular interactions between the NTD and the RdRP palm domain . In order to dissect possible regulatory functions of NTD , we designed mutations at residues Y471 and E472 to perturb key interactions at the NTD-RdRP interface . When crystallized , some of these NS5B interface mutants maintained the interface , while the others adopted an ` open ' conformation that no longer retained the intra-molecular interactions . Data from multiple in vitro RdRP assays indicated that the perturbation of the NTD-RdRP interactions clearly reduced the fidelity level of the RNA synthesis , while the processivity of the NS5B elongation complex was not affected . Collectively , our work demonstrates an explicit and unique mode of polymerase fidelity modulation and provides a vivid example of co-evolution in multi-domain enzymes .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Typically not assisted by proofreading ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"the RNAdependent RNA polymerases ( RdRPs ) encoded by the RNA viruses may need to independently control its fidelity to fulfill virus viability and fitness .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"However , the precise mechanism by which the RdRP maintains its optimal fidelity level remains largely elusive .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"By solving 2.1-2.5 Å resolution crystal structures of the classical swine fever virus ( CSFV ) NS5B ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"an RdRP with a unique naturally fused N-terminal domain ( NTD ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"we identified high-resolution intramolecular interactions between the NTD and the RdRP palm domain .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"In order to dissect possible regulatory functions of NTD ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"we designed mutations at residues Y471 and E472 to perturb key interactions at the NTD-RdRP interface .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"When crystallized , some of these NS5B interface mutants maintained the interface ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"while the others adopted an ` open ' conformation that no longer retained the intra-molecular interactions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Data from multiple in vitro RdRP assays indicated that the perturbation of the NTD-RdRP interactions clearly reduced the fidelity level of the RNA synthesis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"while the processivity of the NS5B elongation complex was not affected .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Collectively , our work demonstrates an explicit and unique mode of polymerase fidelity modulation and provides a vivid example of co-evolution in multi-domain enzymes .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "f8d7bf0b17bd6f014933e63947c95cef41489bd1", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nDiseases likely affect large carnivore demography and can hinder conservation efforts . We considered three highly contagious viruses that infect a wide range of domestic and wild mammals : canine parvovirus type 2 ( CPV-2 ) , canine distemper virus ( CDV ) and canine enteric coronaviruses ( CECoV ) . Infection by either one of these viruses can affect populations through increased mortality and/or decreased general health . We investigated infection in the wolf populations of Abruzzo , Lazio e Molise National Park ( PNALM ) , Italy , and of Mercantour National Park ( PNM ) , France . Faecal samples were collected during one winter , from October to March , from four packs in PNALM ( n = 79 ) and from four packs in PNM ( n = 66 ) . We screened samples for specific sequences of viral nucleic acids . To our knowledge , our study is the first documented report of CECoV infection in wolves outside Alaska , and of the large-scale occurrence of CPV-2 in European wolf populations . The results suggest that CPV-2 is enzootic in the population of PNALM , but not in PNM and that CECoV is episodic in both areas . We did not detect CDV . Our findings suggest that density and spatial distribution of susceptible hosts , in particular free-ranging dogs , can be important factors influencing infections in wolves . This comparative study is an important step in evaluating the nature of possible disease threats in the studied wolf populations . Recent emergence of new viral strains in Europe additionally strengthens the need for proactive monitoring of wolves and other susceptible sympatric species for viral threats and other impairing infections .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Diseases likely affect large carnivore demography and can hinder conservation efforts .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"We considered three highly contagious viruses that infect a wide range of domestic and wild mammals : canine parvovirus type 2 ( CPV-2 ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"canine distemper virus ( CDV ) and canine enteric coronaviruses ( CECoV ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Infection by either one of these viruses can affect populations through increased mortality and/or decreased general health .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"We investigated infection in the wolf populations of Abruzzo ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Lazio e Molise National Park ( PNALM ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Italy , and of Mercantour National Park ( PNM ) , France .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Faecal samples were collected during one winter ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"from October to March , from four packs in PNALM ( n = 79 ) and from four packs in PNM ( n = 66 ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"We screened samples for specific sequences of viral nucleic acids .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"To our knowledge , our study is the first documented report of CECoV infection in wolves outside Alaska ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"and of the large-scale occurrence of CPV-2 in European wolf populations .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"The results suggest that CPV-2 is enzootic in the population of PNALM ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"but not in PNM and that CECoV is episodic in both areas .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"We did not detect CDV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Our findings suggest that density and spatial distribution of susceptible hosts ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"in particular free-ranging dogs , can be important factors influencing infections in wolves .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"This comparative study is an important step in evaluating the nature of possible disease threats in the studied wolf populations .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"Recent emergence of new viral strains in Europe additionally strengthens the need for proactive monitoring of wolves and other susceptible sympatric species for viral threats and other impairing infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}]}"}]}
{"paper_id": "c85ca5217f9051f83911569eed1eb52cf992f7dd", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nEpidemiological and laboratory studies have shown that green tea and green tea catechins exert beneficial effects on a variety of diseases , including cancer , metabolic syndrome , infectious diseases , and neurodegenerative diseases . In most cases , ( − ) - epigallocatechin gallate ( EGCG ) has been shown to play a central role in these effects by green tea . Catechins from other plant sources have also shown health benefits . Many studies have revealed that the binding of EGCG and other catechins to proteins is involved in its action mechanism . Computational docking analysis ( CMDA ) and X-ray crystallographic analysis ( XCA ) have provided detailed information on catechin-protein interactions . Several of these studies have revealed that the galloyl moiety anchors it to the cleft of proteins through interactions with its hydroxyl groups , explaining the higher activity of galloylated catechins such as EGCG and epicatechin gallate than non-galloylated catechins . In this paper , we review the results of CMDA and XCA of EGCG and other plant catechins to understand catechin-protein interactions with the expectation of developing new drugs with health-promoting properties .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Epidemiological and laboratory studies have shown that green tea and green tea catechins exert beneficial effects on a variety of diseases ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"including cancer , metabolic syndrome ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"infectious diseases , and neurodegenerative diseases .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"In most cases , ( − ) - epigallocatechin gallate ( EGCG ) has been shown to play a central role in these effects by green tea .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Catechins from other plant sources have also shown health benefits .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Many studies have revealed that the binding of EGCG and other catechins to proteins is involved in its action mechanism .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"Computational docking analysis ( CMDA ) and X-ray crystallographic analysis ( XCA ) have provided detailed information on catechin-protein interactions .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"Several of these studies have revealed that the galloyl moiety anchors it to the cleft of proteins through interactions with its hydroxyl groups ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"explaining the higher activity of galloylated catechins such as EGCG and epicatechin gallate than non-galloylated catechins .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"In this paper , we review the results of CMDA and XCA of EGCG and other plant catechins to understand catechin-protein interactions with the expectation of developing new drugs with health-promoting properties .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "8d6910ec7ebd72c2827b4bd8c2b74434fecaa6de", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nOnly a few years ago , viral diagnosis was largely an exercise for academic researchers and public health practitioners with focus on epidemiologic analyses and outbreak prevention , detection , and control . Opportunities for therapeutic intervention were limited to only a few applications such as herpesvirus infections , infl uenza , and HIV/AIDS ; hence , once a bacterial or fungal infection was excluded , clinicians were limited to providing supportive care for what was presumed to be a viral syndrome . Public health organizations tracked the incidence of viral infections and the development of resistance to the few antiviral drugs in use and provided input to governments and the pharmaceutical industry regarding selection of vaccine targets . More recently , interest in viral diagnostics has burgeoned with the advent of new tools for detection and discovery , global recognition of pandemic risk , high-throughput drug screening , rational drug design , and immunotherapeutics . An additional impetus has been the implication of viruses in chronic illnesses not previously attributed to infection . The objective of this chapter is to review the factors responsible for the rise in awareness of viral infections , methods for diagnosis and monitoring viral infections , and future prospects for improvements in discovery , detection , and response to the challenges of clinical virology .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Only a few years ago ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"viral diagnosis was largely an exercise for academic researchers and public health practitioners with focus on epidemiologic analyses and outbreak prevention , detection , and control .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Opportunities for therapeutic intervention were limited to only a few applications such as herpesvirus infections ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"infl uenza , and HIV/AIDS ; hence ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"once a bacterial or fungal infection was excluded ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"clinicians were limited to providing supportive care for what was presumed to be a viral syndrome .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"Public health organizations tracked the incidence of viral infections and the development of resistance to the few antiviral drugs in use and provided input to governments and the pharmaceutical industry regarding selection of vaccine targets .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"More recently , interest in viral diagnostics has burgeoned with the advent of new tools for detection and discovery ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"global recognition of pandemic risk ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"high-throughput drug screening , rational drug design , and immunotherapeutics .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"An additional impetus has been the implication of viruses in chronic illnesses not previously attributed to infection .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"The objective of this chapter is to review the factors responsible for the rise in awareness of viral infections ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}, {\"segment_text\": \"methods for diagnosis and monitoring viral infections ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 13}, {\"segment_text\": \"and future prospects for improvements in discovery ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 14}, {\"segment_text\": \"detection , and response to the challenges of clinical virology .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 15}]}"}]}
{"paper_id": "e0359b1b4c6d229299cb7b9f149bc9b943a2077f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Measles caused by a paramyxovirus , characterized by fever , malaise , cough , coryza conjunctivitis , a maculopapular rash is known to result in pneumonia , encephalitis and death . Fatal cases of measles in Sri Lanka are rare after implementation of the National Immunization Programme in 1984 . Thereafter 0.1 % case fatality rate was observed during October 1999-June 2000 which is a very low figure compared to other regional countries . Immunization guidelines were further revised in 2001 , 2011 and in 2012 when additional immunization was recommended to age group 4-21 years ; who are likely to have inadequate immunization , in order to achieve elimination of Measles by 2020 . However , in 2013-2014 , 4690 cases were reported and the majority were children less than 1 year of age . The occurrence in adults is hard to retrieve in published epidemiological reports , however had been 38 % ( out of 1008 patients ) in the 3rd quarter of 2013 . During this outbreak 73/101 ( 72 % ) reported from the North Central Province of Sri Lanka had been more than 12 years of age with 50 % being more than 29 years . 14 Sri lankan adult patients ( median age 32 years ( range 25-48 ) ) who presented sporadically from June 2014 to March 2016 , with confirmed measles infection were enrolled retrospectively after informed consent . Details with regards to their clinical presentation , immunization and other relevant areas were collected using an interviewer administered questionnaire or using patient management records . The patients presented with high fever , headache , severe body aches , sore throat , dry cough , intense tearing , red eyes and posterior cervical lymphadenopathy over 3-5 days duration . Later they developed discrete maculopapular rash helping the diagnosis . They had a variable degree of leucopenia , lymphocytosis , thrombocytopenia and derangements in the liver functions mimicking any other acute febrile illnesses such as dengue , chikungunya , leptospirosis or Zika virus infection . At least a 3-5 day delay in the diagnosis was observed ( even after the appearance of the rash in some patients ) , due to non-awareness of its occurrence , unfamiliarity of measles in adults , non-specific nature of the illness and non-availability of rapid diagnostics , risking transmission to the immune-compromised or non-immune staff or patients . Identification of the source of infection in these sporadic adult cases and their virologic surveillance and molecular epidemiology will be important to interrupt the transmission and to achieve the targeted elimination of measles from Sri Lanka by 2020 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Measles caused by a paramyxovirus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"characterized by fever , malaise ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"cough , coryza conjunctivitis , a maculopapular rash is known to result in pneumonia , encephalitis and death .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Fatal cases of measles in Sri Lanka are rare after implementation of the National Immunization Programme in 1984 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Thereafter 0.1 % case fatality rate was observed during October 1999-June 2000 which is a very low figure compared to other regional countries .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Immunization guidelines were further revised in 2001 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"2011 and in 2012 when additional immunization was recommended to age group 4-21 years ; who are likely to have inadequate immunization ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"in order to achieve elimination of Measles by 2020 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"However , in 2013-2014 , 4690 cases were reported and the majority were children less than 1 year of age .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"The occurrence in adults is hard to retrieve in published epidemiological reports ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"however had been 38 % ( out of 1008 patients ) in the 3rd quarter of 2013 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"During this outbreak 73/101 ( 72 % ) reported from the North Central Province of Sri Lanka had been more than 12 years of age with 50 % being more than 29 years .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"14 Sri lankan adult patients ( median age 32 years ( range 25-48 ) ) who presented sporadically from June 2014 to March 2016 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"with confirmed measles infection were enrolled retrospectively after informed consent .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"Details with regards to their clinical presentation ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 15}, {\"segment_text\": \"immunization and other relevant areas were collected using an interviewer administered questionnaire or using patient management records .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 16}, {\"segment_text\": \"The patients presented with high fever ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"headache , severe body aches ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"sore throat , dry cough ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"intense tearing , red eyes and posterior cervical lymphadenopathy over 3-5 days duration .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}, {\"segment_text\": \"Later they developed discrete maculopapular rash helping the diagnosis .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}, {\"segment_text\": \"They had a variable degree of leucopenia ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 22}, {\"segment_text\": \"lymphocytosis , thrombocytopenia and derangements in the liver functions mimicking any other acute febrile illnesses such as dengue ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 23}, {\"segment_text\": \"chikungunya , leptospirosis or Zika virus infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 24}, {\"segment_text\": \"At least a 3-5 day delay in the diagnosis was observed ( even after the appearance of the rash in some patients ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 25}, {\"segment_text\": \"due to non-awareness of its occurrence ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 26}, {\"segment_text\": \"unfamiliarity of measles in adults ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 27}, {\"segment_text\": \"non-specific nature of the illness and non-availability of rapid diagnostics ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 28}, {\"segment_text\": \"risking transmission to the immune-compromised or non-immune staff or patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 29}, {\"segment_text\": \"Identification of the source of infection in these sporadic adult cases and their virologic surveillance and molecular epidemiology will be important to interrupt the transmission and to achieve the targeted elimination of measles from Sri Lanka by 2020 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 30}]}"}]}
{"paper_id": "24874af5c599f668e87df044bd03bb2743839af2", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBecause of the conflicting data concerning the SARS-CoV inhibitory efficacy of ribavirin , an inosine monophosphate ( IMP ) dehydrogenase inhibitor , studies were done to evaluate the efficacy of ribavirin and other IMP dehydrogenase inhibitors ( 5-ethynyl-1 - ␤ - d-ribofuranosylimidazole-4-carboxamide ( EICAR ) , mizoribine , and mycophenolic acid ) in preventing viral replication in the lungs of BALB/c mice , a replication model for severe acute respiratory syndrome ( SARS ) infections ( Subbarao , K.transfer of neutralizing antibody prevent replication of severe acute respiratory syndrome coronavirus ( SARS-CoV ) in the respiratory tract of mice . J. Virol . 78 , ( 3572 ) ( 3573 ) ( 3574 ) ( 3575 ) ( 3576 ) ( 3577 ) . Ribavirin given at 75 mg/kg 4 h prior to virus exposure and then given twice daily for 3 days beginning at day 0 was found to increase virus lung titers and extend the length of time that virus could be detected in the lungs of mice . Other IMP dehydrogenase inhibitors administered near maximum tolerated doses using the same dosing regimen as for ribavirin were found to slightly enhance virus replication in the lungs . In addition , ribavirin treatment seemed also to promote the production of pro-inflammatory cytokines 4 days after cessation of treatment , although after 3 days of treatment ribavirin inhibited pro-inflammatory cytokine production in infected mice , significantly reducing the levels of the cytokines IL-1 ␣ , interleukin-5 ( IL-5 ) , monocyte chemotactic protein-1 ( MCP-1 ) , and granulocyte-macrophage colony stimulating factor ( GM-CSF ) . These findings suggest that ribavirin may actually contribute to the pathogenesis of SARS-CoV by prolonging and/or enhancing viral replication in the lungs . By not inhibiting viral replication in the lungs of infected mice , ribavirin treatment may have provided a continual source of stimulation for the inflammatory response thought to contribute to the pathogenesis of the infection . Our data do not support the use of ribavirin or other IMP dehydrogenase inhibitors for treating SARS infections in humans .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Because of the conflicting data concerning the SARS-CoV inhibitory efficacy of ribavirin ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"an inosine monophosphate ( IMP ) dehydrogenase inhibitor ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"studies were done to evaluate the efficacy of ribavirin and other IMP dehydrogenase inhibitors ( 5-ethynyl-1 - ␤ - d-ribofuranosylimidazole-4-carboxamide ( EICAR ) ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"mizoribine , and mycophenolic acid ) in preventing viral replication in the lungs of BALB/c mice ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"a replication model for severe acute respiratory syndrome ( SARS ) infections ( Subbarao , K.transfer of neutralizing antibody prevent replication of severe acute respiratory syndrome coronavirus ( SARS-CoV ) in the respiratory tract of mice .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"J. Virol .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 6}, {\"segment_text\": \"78 , ( 3572 ) ( 3573 ) ( 3574 ) ( 3575 ) ( 3576 ) ( 3577 ) .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 7}, {\"segment_text\": \"Ribavirin given at 75 mg/kg 4 h prior to virus exposure and then given twice daily for 3 days beginning at day 0 was found to increase virus lung titers and extend the length of time that virus could be detected in the lungs of mice .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Other IMP dehydrogenase inhibitors administered near maximum tolerated doses using the same dosing regimen as for ribavirin were found to slightly enhance virus replication in the lungs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"In addition , ribavirin treatment seemed also to promote the production of pro-inflammatory cytokines 4 days after cessation of treatment ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"although after 3 days of treatment ribavirin inhibited pro-inflammatory cytokine production in infected mice ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"significantly reducing the levels of the cytokines IL-1 ␣ ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"interleukin-5 ( IL-5 ) , monocyte chemotactic protein-1 ( MCP-1 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"and granulocyte-macrophage colony stimulating factor ( GM-CSF ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"These findings suggest that ribavirin may actually contribute to the pathogenesis of SARS-CoV by prolonging and/or enhancing viral replication in the lungs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"By not inhibiting viral replication in the lungs of infected mice ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"ribavirin treatment may have provided a continual source of stimulation for the inflammatory response thought to contribute to the pathogenesis of the infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Our data do not support the use of ribavirin or other IMP dehydrogenase inhibitors for treating SARS infections in humans .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "8d837ad6865678650be8edee7e35c4b8a4960076", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe Chelonid fibropapilloma-associated herpesvirus ( CFPHV ) is hypothesized to be the causative agent of fibropapillomatosis , a neoplastic disease in sea turtles , given its consistent detection by PCR in fibropapilloma tumours . CFPHV has also been detected recently by PCR in tissue samples from clinically healthy ( non exhibiting fibropapilloma tumours ) turtles , thus representing presumably latent infections of the pathogen . Given that template copy numbers of viruses in latent infections can be very low , extremely sensitive PCR assays are needed to optimize detection efficiency . In this study , efficiency of several PCR assays designed for CFPHV detection is explored and compared to a method published previously . The results show that adoption of a triplet set of singleplex PCR assays outperforms other methods , with an approximately 3-fold increase in detection success in comparison to the standard assay . Thus , a new assay for the detection of CFPHV DNA markers is presented , and adoption of its methodology is recommended in future CFPHV screens among sea turtles .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The Chelonid fibropapilloma-associated herpesvirus ( CFPHV ) is hypothesized to be the causative agent of fibropapillomatosis ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"a neoplastic disease in sea turtles ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"given its consistent detection by PCR in fibropapilloma tumours .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"CFPHV has also been detected recently by PCR in tissue samples from clinically healthy ( non exhibiting fibropapilloma tumours ) turtles ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"thus representing presumably latent infections of the pathogen .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Given that template copy numbers of viruses in latent infections can be very low ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"extremely sensitive PCR assays are needed to optimize detection efficiency .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"In this study , efficiency of several PCR assays designed for CFPHV detection is explored and compared to a method published previously .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"The results show that adoption of a triplet set of singleplex PCR assays outperforms other methods ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"with an approximately 3-fold increase in detection success in comparison to the standard assay .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Thus , a new assay for the detection of CFPHV DNA markers is presented ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and adoption of its methodology is recommended in future CFPHV screens among sea turtles .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "e65b607b21bcb4822a4b28666621b56261176a1d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThis is a prospective observational study of a cohort of inpatients exposed to a severe acute respiratory syndrome ( SARS ) outbreak . Strict infection control policies were instituted . The 70 patients exposed to the SARS outbreak were isolated from the rest of the hospital . They were triaged , quarantined and cohorted in three open plan wards . Selective isolation was carried out immediately when symptoms and signs suspicious of SARS manifested clinically . The patients ' ages ranged from 21 to 90 years and 56 % had surgery before the quarantine . Sixteen patients with unexplained fever during the period of quarantine were isolated , seven of whom were eventually diagnosed with probable SARS . The crude incidence of SARS in our cohort was 10 % . The SARS case fatality was 14 % . No secondary transmission of the SARS virus within the cohort was observed . Strict infection control , together with appropriate triaging , cohorting and selective isolation , is an effective and practical model of intervention in cohorts exposed to a SARS outbreak . Such a management strategy eases the logistic constraints imposed by demands for large numbers of isolation facilities in the face of a massive outbreak .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"This is a prospective observational study of a cohort of inpatients exposed to a severe acute respiratory syndrome ( SARS ) outbreak .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Strict infection control policies were instituted .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"The 70 patients exposed to the SARS outbreak were isolated from the rest of the hospital .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"They were triaged , quarantined and cohorted in three open plan wards .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Selective isolation was carried out immediately when symptoms and signs suspicious of SARS manifested clinically .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"The patients ' ages ranged from 21 to 90 years and 56 % had surgery before the quarantine .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Sixteen patients with unexplained fever during the period of quarantine were isolated ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"seven of whom were eventually diagnosed with probable SARS .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The crude incidence of SARS in our cohort was 10 % .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"The SARS case fatality was 14 % .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"No secondary transmission of the SARS virus within the cohort was observed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Strict infection control , together with appropriate triaging ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"cohorting and selective isolation , is an effective and practical model of intervention in cohorts exposed to a SARS outbreak .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Such a management strategy eases the logistic constraints imposed by demands for large numbers of isolation facilities in the face of a massive outbreak .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "e7e867dee6c709585ea080cb628e430931d9fad7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\n| The rapid accumulation of complete genomic sequences offers the opportunity to carry out an analysis of inter-and intra-individual genome variation within a species on a routine basis . Sequencing whole genomes requires resources that are currently beyond those of a single laboratory and therefore it is not a practical approach for resequencing hundreds of individual genomes . DNA microarrays present an alternative way to study differences between closely related genomes . Advances in microarray-based approaches have enabled the main forms of genomic variation ( amplifications , deletions , insertions , rearrangements and base-pair changes ) to be detected using techniques that are readily performed in individual laboratories using simple experimental approaches .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"| The rapid accumulation of complete genomic sequences offers the opportunity to carry out an analysis of inter-and intra-individual genome variation within a species on a routine basis .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Sequencing whole genomes requires resources that are currently beyond those of a single laboratory and therefore it is not a practical approach for resequencing hundreds of individual genomes .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"DNA microarrays present an alternative way to study differences between closely related genomes .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Advances in microarray-based approaches have enabled the main forms of genomic variation ( amplifications , deletions , insertions , rearrangements and base-pair changes ) to be detected using techniques that are readily performed in individual laboratories using simple experimental approaches .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}]}"}]}
{"paper_id": "06190bfcbc53a5d5d17e0a60a3a0f6488d8ae1db", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe recent outbreak of the human Zaire ebolavirus ( EBOV ) epidemic is spiraling out of control in West Africa . Human EBOV hemorrhagic fever has a case fatality rate of up to 90 % . The EBOV is classified as a biosafety level 4 pathogen and is considered a category A agent of bioterrorism by Centers for Disease Control and Prevention , with no approved therapies and vaccines available for its treatment apart from supportive care . Although several promising therapeutic agents and vaccines against EBOV are undergoing the Phase I human trial , the current epidemic might be outpacing the speed at which drugs and vaccines can be produced . Like all viruses , the EBOV largely relies on host cell factors and physiological processes for its entry , replication , and egress . We have reviewed currently available therapeutic agents that have been shown to be effective in suppressing the proliferation of the EBOV in cell cultures or animal studies . Most of the therapeutic agents in this review are directed against non-mutable targets of the host , which is independent of viral mutation . These medications are approved by the Food and Drug Administration ( FDA ) for the treatment of other diseases . They are available and stockpileable for immediate use . They may also have a complementary role to those therapeutic agents under development that are directed against the mutable targets of the EBOV .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The recent outbreak of the human Zaire ebolavirus ( EBOV ) epidemic is spiraling out of control in West Africa .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Human EBOV hemorrhagic fever has a case fatality rate of up to 90 % .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The EBOV is classified as a biosafety level 4 pathogen and is considered a category A agent of bioterrorism by Centers for Disease Control and Prevention ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"with no approved therapies and vaccines available for its treatment apart from supportive care .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Although several promising therapeutic agents and vaccines against EBOV are undergoing the Phase I human trial ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"the current epidemic might be outpacing the speed at which drugs and vaccines can be produced .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Like all viruses , the EBOV largely relies on host cell factors and physiological processes for its entry , replication , and egress .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"We have reviewed currently available therapeutic agents that have been shown to be effective in suppressing the proliferation of the EBOV in cell cultures or animal studies .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"Most of the therapeutic agents in this review are directed against non-mutable targets of the host ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"which is independent of viral mutation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"These medications are approved by the Food and Drug Administration ( FDA ) for the treatment of other diseases .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"They are available and stockpileable for immediate use .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"They may also have a complementary role to those therapeutic agents under development that are directed against the mutable targets of the EBOV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "e533d3f826842f863a178112f8d2888669b7bbe7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe serotonin transporter ( SERT ) , a member of the neurotransmitter sodium symporter ( NSS ) family , is responsible for the reuptake of serotonin from the synaptic cleft to maintain neurotransmitter homeostasis . SERT is established as an important target in the treatment of anxiety and depression . Because a high-resolution crystal structure is not available , a computational model of SERT was built based upon the x-ray coordinates of the leucine transporter LeuT , a bacterial NSS homolog . The model was used to develop the first SERT structure-based pharmacophore . Virtual screening ( VS ) of a small molecule structural library using the generated SERT computational model yielded candidate ligands of diverse scaffolds . Pharmacological analysis of the VS hits identified two SERT-selective compounds , potential lead compounds for further SERT-related medication development .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The serotonin transporter ( SERT ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"a member of the neurotransmitter sodium symporter ( NSS ) family ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"is responsible for the reuptake of serotonin from the synaptic cleft to maintain neurotransmitter homeostasis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"SERT is established as an important target in the treatment of anxiety and depression .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Because a high-resolution crystal structure is not available ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"a computational model of SERT was built based upon the x-ray coordinates of the leucine transporter LeuT , a bacterial NSS homolog .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"The model was used to develop the first SERT structure-based pharmacophore .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Virtual screening ( VS ) of a small molecule structural library using the generated SERT computational model yielded candidate ligands of diverse scaffolds .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Pharmacological analysis of the VS hits identified two SERT-selective compounds ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"potential lead compounds for further SERT-related medication development .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}]}"}]}
{"paper_id": "7d301792a867c9978ec19acd7ed798c856b823e5", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPorcine transmissible gastroenteritis virus ( TGEV ) is one of the major etiological agents of viral enteritis and fetal diarrhea in suckling piglets . In this study , a TGEV JS2012 strain was isolated from the feces of piglets in Jiangsu Province , China . The phylogenetic analysis showed that TGEV JS2012 was placed between the Purdue and the Miller clusters . Analysis of recombination confirmed that TGEV JS2012 is a natural recombinant strain between Miller M6 and Purdue 115 . Similar to Miller M6 , virulent Purdue and China strain TS , in S gene the JS2012 maintained genetic integrity and the characteristics of the TGEV virulent strains . In vivo , TGEV JS2012 caused 100 % mortality in newborn piglets , indicating the strong pathogenicity of this isolate . These results reveal that the JS2012 is a novel natural recombinant TGEV with high virulence . Our findings provide valuable information about genetic diversity and infection mechanism of the coronavirus family .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Porcine transmissible gastroenteritis virus ( TGEV ) is one of the major etiological agents of viral enteritis and fetal diarrhea in suckling piglets .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"In this study , a TGEV JS2012 strain was isolated from the feces of piglets in Jiangsu Province , China .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"The phylogenetic analysis showed that TGEV JS2012 was placed between the Purdue and the Miller clusters .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"Analysis of recombination confirmed that TGEV JS2012 is a natural recombinant strain between Miller M6 and Purdue 115 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Similar to Miller M6 , virulent Purdue and China strain TS ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"in S gene the JS2012 maintained genetic integrity and the characteristics of the TGEV virulent strains .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"In vivo , TGEV JS2012 caused 100 % mortality in newborn piglets ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"indicating the strong pathogenicity of this isolate .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"These results reveal that the JS2012 is a novel natural recombinant TGEV with high virulence .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Our findings provide valuable information about genetic diversity and infection mechanism of the coronavirus family .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}]}"}]}
{"paper_id": "b11b26f30a25036589753cd3ec28b64bc2633838", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe ongoing outbreak of COVID-19 that began in Wuhan , China , has constituted a Public Health Emergency of International Concern , with cases confirmed in multiple countries . Currently , patients are the primary source of infection . We report a confirmed case of COVID-19 whose oropharyngeal swab test of SARS-CoV-2 RNA turned positive in convalescence . This case highlights the importance of active surveillance of SARS-CoV-2 RNA for infectivity assessment .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The ongoing outbreak of COVID-19 that began in Wuhan ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"China , has constituted a Public Health Emergency of International Concern ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"with cases confirmed in multiple countries .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Currently , patients are the primary source of infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"We report a confirmed case of COVID-19 whose oropharyngeal swab test of SARS-CoV-2 RNA turned positive in convalescence .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"This case highlights the importance of active surveillance of SARS-CoV-2 RNA for infectivity assessment .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}]}"}]}
{"paper_id": "597d89cc2fd0051ce2c08589fab6c7f5ea822e36", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe coronavirus nucleocapsid ( N ) protein is a major structural component of virions that associates with the genomic RNA to form a helical nucleocapsid . N appears to be a multifunctional protein since data also suggest that the protein may be involved in viral RNA replication and translation . All of these functions presumably involve interactions between N and viral RNAs . As a step toward understanding how N interacts with viral RNAs , we mapped high-efficiency N-binding sites within BCV-and MHV-defective genomes . Both in vivo and in vitro assays were used to study binding of BCV and MHV N proteins to viral and nonviral RNAs . N-viral RNA complexes were detected in bovine coronavirus ( BCV ) - infected cells and in cells transiently expressing the N protein . Filter binding was used to map N-binding sites within Drep , a BCV-defective genome that is replicated and packaged in the presence of helper virus . One high-efficiency N-binding site was identified between nucleotides 1441 and 1875 at the 3Ј end of the N ORF within Drep . For comparative purposes N-binding sites were also mapped for the mouse hepatitis coronavirus ( MHV ) - defective interfering ( DI ) RNA MIDI-C . Binding efficiencies similar to those for Drep were measured for RNA transcripts of a region encompassing the MHV packaging signal ( nts 3949-4524 ) , as well as a region at the 3Ј end of the MHV N ORF ( nts 4837-5197 ) within MIDI-C . Binding to the full-length MIDI-C transcript ( ϳ5500 nts ) and to an ϳ1-kb transcript from the gene 1a region ( nts 935-1986 ) of MIDI-C that excluded the packaging signal were both significantly higher than that measured for the smaller transcripts . This is the first identification of N-binding sequences for BCV . It is also the first report to demonstrate that N interacts in vitro with sequences other than the packaging signal and leader within the MHV genome . The data clearly demonstrate that N binds coronavirus RNAs more efficiently than nonviral RNAs . The results have implications with regard to the multifunctional role of N.\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The coronavirus nucleocapsid ( N ) protein is a major structural component of virions that associates with the genomic RNA to form a helical nucleocapsid .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"N appears to be a multifunctional protein since data also suggest that the protein may be involved in viral RNA replication and translation .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"All of these functions presumably involve interactions between N and viral RNAs .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"As a step toward understanding how N interacts with viral RNAs ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"we mapped high-efficiency N-binding sites within BCV-and MHV-defective genomes .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Both in vivo and in vitro assays were used to study binding of BCV and MHV N proteins to viral and nonviral RNAs .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"N-viral RNA complexes were detected in bovine coronavirus ( BCV ) - infected cells and in cells transiently expressing the N protein .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Filter binding was used to map N-binding sites within Drep ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"a BCV-defective genome that is replicated and packaged in the presence of helper virus .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"One high-efficiency N-binding site was identified between nucleotides 1441 and 1875 at the 3Ј end of the N ORF within Drep .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"For comparative purposes N-binding sites were also mapped for the mouse hepatitis coronavirus ( MHV ) - defective interfering ( DI ) RNA MIDI-C .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Binding efficiencies similar to those for Drep were measured for RNA transcripts of a region encompassing the MHV packaging signal ( nts 3949-4524 ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"as well as a region at the 3Ј end of the MHV N ORF ( nts 4837-5197 ) within MIDI-C .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"Binding to the full-length MIDI-C transcript ( ϳ5500 nts ) and to an ϳ1-kb transcript from the gene 1a region ( nts 935-1986 ) of MIDI-C that excluded the packaging signal were both significantly higher than that measured for the smaller transcripts .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"This is the first identification of N-binding sequences for BCV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"It is also the first report to demonstrate that N interacts in vitro with sequences other than the packaging signal and leader within the MHV genome .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"The data clearly demonstrate that N binds coronavirus RNAs more efficiently than nonviral RNAs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"The results have implications with regard to the multifunctional role of N.\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}]}"}]}
{"paper_id": "0f06fc59914545bf3fdd7ae0b2cd8fe2a4208ace", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nStress Granules ( SGs ) are dynamic ribonucleoprotein aggregates , which have been observed in cells subjected to environmental stresses , such as oxidative stress and heat shock ( HS ) . Although pluripotent stem cells ( PSCs ) are highly sensitive to oxidative stress , the role of SGs in regulating PSC self-renewal and differentiation has not been fully elucidated . Here we found that sodium arsenite ( SA ) and HS , but not hydrogen peroxide ( H 2 O 2 ) , induce SG formation in human induced ( hi ) PSCs . Particularly , we found that these granules contain the well-known SG proteins ( G3BP , TIAR , eIF4E , eIF4A , eIF3B , eIF4G , and PABP ) , were found in juxtaposition to processing bodies ( PBs ) , and were disassembled after the removal of the stress . Moreover , we showed that SA and HS , but not H 2 O 2 , promote eIF2α phosphorylation in hiPSCs forming SGs . Analysis of pluripotent protein expression showed that HS significantly reduced all tested markers ( OCT4 , SOX2 , NANOG , KLF4 , L1TD1 , and LIN28A ) , while SA selectively reduced the expression levels of NANOG and L1TD1 . Finally , in addition to LIN28A and L1TD1 , we identified DPPA5 ( pluripotent protein marker ) as a novel component of SGs . Collectively , these results provide new insights into the molecular cues of hiPSCs responses to environmental insults .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Stress Granules ( SGs ) are dynamic ribonucleoprotein aggregates ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"which have been observed in cells subjected to environmental stresses ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"such as oxidative stress and heat shock ( HS ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Although pluripotent stem cells ( PSCs ) are highly sensitive to oxidative stress ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"the role of SGs in regulating PSC self-renewal and differentiation has not been fully elucidated .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Here we found that sodium arsenite ( SA ) and HS ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"but not hydrogen peroxide ( H 2 O 2 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"induce SG formation in human induced ( hi ) PSCs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Particularly , we found that these granules contain the well-known SG proteins ( G3BP , TIAR , eIF4E , eIF4A , eIF3B , eIF4G , and PABP ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"were found in juxtaposition to processing bodies ( PBs ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"and were disassembled after the removal of the stress .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Moreover , we showed that SA and HS ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"but not H 2 O 2 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"promote eIF2α phosphorylation in hiPSCs forming SGs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Analysis of pluripotent protein expression showed that HS significantly reduced all tested markers ( OCT4 , SOX2 , NANOG , KLF4 , L1TD1 , and LIN28A ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"while SA selectively reduced the expression levels of NANOG and L1TD1 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Finally , in addition to LIN28A and L1TD1 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"we identified DPPA5 ( pluripotent protein marker ) as a novel component of SGs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Collectively , these results provide new insights into the molecular cues of hiPSCs responses to environmental insults .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}]}"}]}
{"paper_id": "8c7d6b3f5280ce7538e515530b18e837203c6af9", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nInterferon inducible transmembrane protein ( IFITM ) family genes have been implicated in several cellular processes such as the homotypic cell adhesion functions of IFNs and cellular anti-proliferative activities . We previously showed that the IFITM3 single nucleotide polymorphisms ( SNPs ) associated with susceptibility to ulcerative colitis ( UC ) . The present study aimed to investigate whether the polymorphisms in the IFITM1 gene are associated with susceptibility to UC . We also evaluated the expression levels in the putative functional promoter polymorphisms to determine the change of their activity . Gene expression profiles in the tissues obtained from human digestive tracts by RT-PCR , and the possible variation sites and SNPs of IFITM1 were identified by direct sequencing method . Genotype analysis in the IFITM1 SNPs was performed by high resolution melting and TaqMan probe analysis , and the haplotype frequencies of IFITM1 SNPs for multiple loci were estimated using the expectation maximization ( EM ) algorithm . The expression levels in the putative functional promoter polymorphisms were evaluated by performing a luciferase reporter assay . We identified two SNPs and two variation sites , g.-1920G > A ( rs77537847 ) , g.-1547delA ( novel ) and g.-416C > G ( rs11246062 ) in the promoter region , and g. 364delA ( rs200576757 ) in intron 1 . The genotype and allele frequencies of the g.-1920G > A polymorphism of IFITM1 gene in the UC patients were significantly different from those of the healthy controls ( P = 0.002 and 0.042 , respectively ) . These results suggest that the g.-1920G > A polymorphism in IFITM1 may be associated with susceptibility to UC .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Interferon inducible transmembrane protein ( IFITM ) family genes have been implicated in several cellular processes such as the homotypic cell adhesion functions of IFNs and cellular anti-proliferative activities .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"We previously showed that the IFITM3 single nucleotide polymorphisms ( SNPs ) associated with susceptibility to ulcerative colitis ( UC ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"The present study aimed to investigate whether the polymorphisms in the IFITM1 gene are associated with susceptibility to UC .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"We also evaluated the expression levels in the putative functional promoter polymorphisms to determine the change of their activity .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Gene expression profiles in the tissues obtained from human digestive tracts by RT-PCR ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"and the possible variation sites and SNPs of IFITM1 were identified by direct sequencing method .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Genotype analysis in the IFITM1 SNPs was performed by high resolution melting and TaqMan probe analysis ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"and the haplotype frequencies of IFITM1 SNPs for multiple loci were estimated using the expectation maximization ( EM ) algorithm .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The expression levels in the putative functional promoter polymorphisms were evaluated by performing a luciferase reporter assay .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"We identified two SNPs and two variation sites ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"g.-1920G > A ( rs77537847 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"g.-1547delA ( novel ) and g.-416C > G ( rs11246062 ) in the promoter region ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"and g. 364delA ( rs200576757 ) in intron 1 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"The genotype and allele frequencies of the g.-1920G > A polymorphism of IFITM1 gene in the UC patients were significantly different from those of the healthy controls ( P = 0.002 and 0.042 , respectively ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"These results suggest that the g.-1920G > A polymorphism in IFITM1 may be associated with susceptibility to UC .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}]}"}]}
{"paper_id": "f87e3aecf44fa8b5a91ce4a82ff8adaa945464c0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe 3 % end of the turkey coronavirus ( TCV ) genome ( 1740 bases ) including the nucleocapsid ( N ) gene and 3 % untranslated region ( UTR ) were sequenced and compared with published sequences of other avian and mammalian coronaviruses . The deduced sequence of the TCV N protein was determined to be 409 amino acids with a molecular mass of approximately 45 kDa . The TCV N protein was identical in size and had greater than 90 % amino acid identity with published N protein sequences of infectious bronchitis virus ( IBV ) ; less than 21 % identity was observed with N proteins of bovine coronavirus and transmissible gastroenteritis virus . The 3 % UTR showed some variation among the three TCV strains examined , with two TCV strains , Minnesota and Indiana , containing 153 base segments which are not present in the NC95 strain . Nucleotide sequence identity between the 3 % UTRs of TCV and IBV was greater than 78 % . Similarities in both size and sequence of TCV and IBV N proteins and 3 % UTRs provide additional evidence that these avian coronaviruses are closely related .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The 3 % end of the turkey coronavirus ( TCV ) genome ( 1740 bases ) including the nucleocapsid ( N ) gene and 3 % untranslated region ( UTR ) were sequenced and compared with published sequences of other avian and mammalian coronaviruses .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 1}, {\"segment_text\": \"The deduced sequence of the TCV N protein was determined to be 409 amino acids with a molecular mass of approximately 45 kDa .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"The TCV N protein was identical in size and had greater than 90 % amino acid identity with published N protein sequences of infectious bronchitis virus ( IBV ) ; less than 21 % identity was observed with N proteins of bovine coronavirus and transmissible gastroenteritis virus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"The 3 % UTR showed some variation among the three TCV strains examined ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"with two TCV strains , Minnesota and Indiana ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"containing 153 base segments which are not present in the NC95 strain .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Nucleotide sequence identity between the 3 % UTRs of TCV and IBV was greater than 78 % .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Similarities in both size and sequence of TCV and IBV N proteins and 3 % UTRs provide additional evidence that these avian coronaviruses are closely related .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}]}"}]}
{"paper_id": "76774987e549a1e89a4b73189cc630193ed25e72", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMass spectrometry ( MS ) has found numerous applications in life sciences . It has high accuracy , sensitivity and wide dynamic range in addition to medium-to high-throughput capabilities . These features make MS a superior platform for analysis of various biomolecules including proteins , lipids , nucleic acids and carbohydrates . Until recently , MS was applied for protein detection and characterization . During the last decade , however , MS has successfully been used for molecular diagnostics of microbial and viral infections with the most notable applications being identification of pathogens , genomic sequencing , mutation detection , DNA methylation analysis , tracking of transmissions , and characterization of genetic heterogeneity . These new developments vastly expand the MS application from experimental research to public health and clinical fields . Matching of molecular techniques with specific requirements of the major MS platforms has produced powerful technologies for molecular diagnostics , which will further benefit from coupling with computational tools for extracting clinical information from MS-derived data .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Mass spectrometry ( MS ) has found numerous applications in life sciences .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"It has high accuracy , sensitivity and wide dynamic range in addition to medium-to high-throughput capabilities .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"These features make MS a superior platform for analysis of various biomolecules including proteins ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"lipids , nucleic acids and carbohydrates .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Until recently , MS was applied for protein detection and characterization .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"During the last decade , however ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"MS has successfully been used for molecular diagnostics of microbial and viral infections with the most notable applications being identification of pathogens ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"genomic sequencing , mutation detection ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"DNA methylation analysis , tracking of transmissions ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"and characterization of genetic heterogeneity .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"These new developments vastly expand the MS application from experimental research to public health and clinical fields .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"Matching of molecular techniques with specific requirements of the major MS platforms has produced powerful technologies for molecular diagnostics ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"which will further benefit from coupling with computational tools for extracting clinical information from MS-derived data .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}]}"}]}
{"paper_id": "40cdf2909c24827365de82a6a5d84a7c3aec0290", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPathogens that spill over between species cause a significant human and animal health burden . Here , we describe characteristics of animal reservoirs that are required for pathogen spillover . We assembled and analyzed a database of 330 disease systems in which a pathogen spills over from a reservoir of one or more species . Three-quarters of reservoirs included wildlife , and 84 % included mammals . Further , 65 % of pathogens depended on a community of reservoir hosts , rather than a single species , for persistence . Among mammals , the most frequently identified reservoir hosts were rodents , artiodactyls , and carnivores . The distribution among orders of mammalian species identified as reservoirs did not differ from that expected by chance . Among disease systems with high priority pathogens and epidemic potential , we found birds , primates , and bats to be overrepresented . We also analyzed the life history traits of mammalian reservoir hosts and compared them to mammals as a whole . Reservoir species had faster life history characteristics than mammals overall , exhibiting traits associated with greater reproductive output rather than long-term survival . Thus , we find that in many respects , reservoirs of spillover pathogens are indeed special . The described patterns provide a useful resource for studying and managing emerging infectious diseases .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Pathogens that spill over between species cause a significant human and animal health burden .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Here , we describe characteristics of animal reservoirs that are required for pathogen spillover .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"We assembled and analyzed a database of 330 disease systems in which a pathogen spills over from a reservoir of one or more species .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Three-quarters of reservoirs included wildlife ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"and 84 % included mammals .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Further , 65 % of pathogens depended on a community of reservoir hosts ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"rather than a single species , for persistence .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Among mammals , the most frequently identified reservoir hosts were rodents , artiodactyls , and carnivores .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"The distribution among orders of mammalian species identified as reservoirs did not differ from that expected by chance .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Among disease systems with high priority pathogens and epidemic potential ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"we found birds , primates ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and bats to be overrepresented .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"We also analyzed the life history traits of mammalian reservoir hosts and compared them to mammals as a whole .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Reservoir species had faster life history characteristics than mammals overall ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"exhibiting traits associated with greater reproductive output rather than long-term survival .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Thus , we find that in many respects ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"reservoirs of spillover pathogens are indeed special .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"The described patterns provide a useful resource for studying and managing emerging infectious diseases .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}]}"}]}
{"paper_id": "e8c619b901c3fd4c2e830df5c471e7b7d204be6b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAn increasing body of evidence highlights the role of host genetic variation in driving susceptibility to severe disease following pathogen infection . In order to fully appreciate the importance of host genetics on infection susceptibility and resulting disease , genetically variable experimental model systems should be employed . These systems allow for the identification , characterization , and mechanistic dissection of genetic variants that cause differential disease responses . Herein we discuss application of the Collaborative Cross ( CC ) panel of recombinant inbred strains to study viral pathogenesis , focusing on practical considerations for experimental design , assessment and analysis of disease responses within the CC , as well as some of the resources developed for the CC . Although the focus of this chapter is on viral pathogenesis , many of the methods presented within are applicable to studies of other pathogens , as well as to case-control designs in genetically diverse populations .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"An increasing body of evidence highlights the role of host genetic variation in driving susceptibility to severe disease following pathogen infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"In order to fully appreciate the importance of host genetics on infection susceptibility and resulting disease ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"genetically variable experimental model systems should be employed .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"These systems allow for the identification ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"characterization , and mechanistic dissection of genetic variants that cause differential disease responses .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Herein we discuss application of the Collaborative Cross ( CC ) panel of recombinant inbred strains to study viral pathogenesis ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"focusing on practical considerations for experimental design ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"assessment and analysis of disease responses within the CC ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"as well as some of the resources developed for the CC .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}, {\"segment_text\": \"Although the focus of this chapter is on viral pathogenesis ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 10}, {\"segment_text\": \"many of the methods presented within are applicable to studies of other pathogens ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 11}, {\"segment_text\": \"as well as to case-control designs in genetically diverse populations .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}]}"}]}
{"paper_id": "eae636d786708e8b229d952affd28b9ea8321bc4", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIn calves , passive immunity of immunoglobulins can be acquired through ingestion of colostrum or colostrum replacers . Plasma can been used to supplement immunoglobulins in healthy or sick calves . Serum half-life of colostral derived immuglobulin G ( IgG ) is estimated to be 20 days . Half-life of IgG is important in determining response to antigens and timing of vaccination in calves . To date studies evaluating half-life of colostrum replacer or plasma derived IgG are lacking . The objectives of this study were to compare the serum halflife of IgG derived from colostrum , colostrum replacer and plasma in dairy calves reared up to 35 days of age . Thirty Jersey calves were randomly assigned to receive colostrum or colostrum replacer by oroesophageal tubing or plasma by intravenous administration . Serum samples were collected at 2 , 5 , 7 , 10 , 14 , 21 , 28 and 35 days . Serum IgG concentrations were determined by radial immunodiffusion . The results indicated that half-life for IgG in colostrum fed ( 28.5 days ) or plasma transfused calves ( 27.3 days ) was longer than colostrum replacer fed calves ( 19.1 days ) . Further studies are required to evaluate pathogen specific immunoglobulins in order to recommend vaccination timing in calves fed colostrum replacers .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"In calves , passive immunity of immunoglobulins can be acquired through ingestion of colostrum or colostrum replacers .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Plasma can been used to supplement immunoglobulins in healthy or sick calves .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Serum half-life of colostral derived immuglobulin G ( IgG ) is estimated to be 20 days .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Half-life of IgG is important in determining response to antigens and timing of vaccination in calves .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"To date studies evaluating half-life of colostrum replacer or plasma derived IgG are lacking .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"The objectives of this study were to compare the serum halflife of IgG derived from colostrum ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"colostrum replacer and plasma in dairy calves reared up to 35 days of age .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"Thirty Jersey calves were randomly assigned to receive colostrum or colostrum replacer by oroesophageal tubing or plasma by intravenous administration .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Serum samples were collected at 2 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"5 , 7 , 10 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"14 , 21 , 28 and 35 days .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Serum IgG concentrations were determined by radial immunodiffusion .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"The results indicated that half-life for IgG in colostrum fed ( 28.5 days ) or plasma transfused calves ( 27.3 days ) was longer than colostrum replacer fed calves ( 19.1 days ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Further studies are required to evaluate pathogen specific immunoglobulins in order to recommend vaccination timing in calves fed colostrum replacers .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "d50837c2e42d8eccc71b5641957ec2a0ed725fdd", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nEmerging infections have threatened humanity since times immemorial . The dramatic anthropogenic , behavioral and social changes that have affected humanity and the environment in the past century have accelerated the intrusion of novel pathogens into the global human population , sometimes with devastating consequences . The AIDS and influenza pandemics have claimed and will continue to claim millions of lives . The recent SARS and Ebola epidemics have threatened populations across borders . The emergence of MERS may well be warning signals of a nascent pandemic threat , while the potential for geographical spread of vector-borne diseases , such as Zika , but also Dengue and Chikungunya is unprecedented . Novel technologies and innovative approaches have multiplied to address and improve response preparedness towards the increasing yet unpredictable threat posed by emerging pathogens .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Emerging infections have threatened humanity since times immemorial .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The dramatic anthropogenic , behavioral and social changes that have affected humanity and the environment in the past century have accelerated the intrusion of novel pathogens into the global human population , sometimes with devastating consequences .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The AIDS and influenza pandemics have claimed and will continue to claim millions of lives .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"The recent SARS and Ebola epidemics have threatened populations across borders .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"The emergence of MERS may well be warning signals of a nascent pandemic threat ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"while the potential for geographical spread of vector-borne diseases ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"such as Zika , but also Dengue and Chikungunya is unprecedented .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Novel technologies and innovative approaches have multiplied to address and improve response preparedness towards the increasing yet unpredictable threat posed by emerging pathogens .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}]}"}]}
{"paper_id": "e977ca94d7eb88b4b650c25c3543e9d48afd535b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nInfectious disease outbreaks often have consequences beyond human health , including concern among the population , economic instability , and sometimes violence . A warning system capable of anticipating social disruptions resulting from disease outbreaks is urgently needed to help decision makers prepare appropriately . We designed a system that operates in near real-time to identify and predict social response . Over 150,000 Internet-based news articles related to outbreaks of 16 diseases in 72 countries and territories were provided by HealthMap . These articles were automatically tagged with indicators of the disease activity and population reaction . An anomaly detection algorithm was implemented on the population reaction indicators to identify periods of unusually severe social response . Then a model was developed to predict the probability of these periods of unusually severe social response occurring in the coming week , 2 and 3 weeks . This model exhibited remarkably strong performance for diseases with substantial media coverage . For country-disease pairs with a median of 20 or more articles per year , the onset of social response in the next week was correctly predicted over 60 % of the time , and 87 % of weeks were correctly predicted . Performance was weaker for diseases with little media coverage , and , for these diseases , the main utility of our system is in identifying social response when it occurs , rather than predicting when it will happen in the future . Overall , the developed near real-time prediction approach is a promising step toward developing predictive models to inform responders of the likely social consequences of disease spread . This research was funded by Defense Threat Reduction Agency ( www.dtra.mil ) contact HDTRA1-12-C-0061 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Infectious disease outbreaks often have consequences beyond human health ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"including concern among the population ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"economic instability , and sometimes violence .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"A warning system capable of anticipating social disruptions resulting from disease outbreaks is urgently needed to help decision makers prepare appropriately .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"We designed a system that operates in near real-time to identify and predict social response .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Over 150,000 Internet-based news articles related to outbreaks of 16 diseases in 72 countries and territories were provided by HealthMap .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"These articles were automatically tagged with indicators of the disease activity and population reaction .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"An anomaly detection algorithm was implemented on the population reaction indicators to identify periods of unusually severe social response .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Then a model was developed to predict the probability of these periods of unusually severe social response occurring in the coming week , 2 and 3 weeks .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"This model exhibited remarkably strong performance for diseases with substantial media coverage .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"For country-disease pairs with a median of 20 or more articles per year ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"the onset of social response in the next week was correctly predicted over 60 % of the time ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"and 87 % of weeks were correctly predicted .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Performance was weaker for diseases with little media coverage ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"and , for these diseases ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"the main utility of our system is in identifying social response when it occurs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"rather than predicting when it will happen in the future .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Overall , the developed near real-time prediction approach is a promising step toward developing predictive models to inform responders of the likely social consequences of disease spread .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"This research was funded by Defense Threat Reduction Agency ( www.dtra.mil ) contact HDTRA1-12-C-0061 .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 19}]}"}]}
{"paper_id": "8b7d76ba81c3eb5ddf6e9330e16ce1189fe1f08b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Mesenchymal stem ( stromal ) cells ( MSCs ) mediate their immunoregulatory and tissue repair functions by secreting paracrine factors , including extracellular vesicles ( EVs ) . In several animal models of human diseases , MSC-EVs mimic the beneficial effects of MSCs . Influenza viruses cause annual outbreaks of acute respiratory illness resulting in significant mortality and morbidity . Influenza viruses constantly evolve , thus generating drug-resistant strains and rendering current vaccines less effective against the newly generated strains . Therefore , new therapies that can control virus replication and the inflammatory response of the host are needed . The objective of this study was to examine if MSC-EV treatment can attenuate influenza virus-induced acute lung injury in a preclinical model . Methods : We isolated EVs from swine bone marrow-derived MSCs . Morphology of MSC-EVs was determined by electron microscopy and expression of mesenchymal markers was examined by flow cytometry . Next , we examined the anti-influenza activity of MSC-EVs in vitro in lung epithelial cells and anti-viral and immunomodulatory properties in vivo in a pig model of influenza virus .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Mesenchymal stem ( stromal ) cells ( MSCs ) mediate their immunoregulatory and tissue repair functions by secreting paracrine factors ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"including extracellular vesicles ( EVs ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"In several animal models of human diseases ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"MSC-EVs mimic the beneficial effects of MSCs .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Influenza viruses cause annual outbreaks of acute respiratory illness resulting in significant mortality and morbidity .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Influenza viruses constantly evolve , thus generating drug-resistant strains and rendering current vaccines less effective against the newly generated strains .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"Therefore , new therapies that can control virus replication and the inflammatory response of the host are needed .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"The objective of this study was to examine if MSC-EV treatment can attenuate influenza virus-induced acute lung injury in a preclinical model .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"Methods : We isolated EVs from swine bone marrow-derived MSCs .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Morphology of MSC-EVs was determined by electron microscopy and expression of mesenchymal markers was examined by flow cytometry .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Next , we examined the anti-influenza activity of MSC-EVs in vitro in lung epithelial cells and anti-viral and immunomodulatory properties in vivo in a pig model of influenza virus .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}]}"}]}
{"paper_id": "be0d004544c7da98785d19f9b3aaf36745da7afe", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAim of this study was to de termine and furthe r characte rize the se rum aminope ptidase - M in childre n with live r dise ase s. Based on our ne w assay , we have shown two fractions of the e nzyme . Activity of the ® rst fraction is e xpre sse d in undilute d se rum at pH adjuste d from 8.5 ( pH of storage d se rum ) to 7.4 . Activity of the se cond fraction ( cryptic activity ) appe ars in the serum ( pH 7.4 ) as a result of dilution and/or addition of aniline naphthale ne sulfonic acid . In childre n with Alagille syndrome , e xtrahe patic biliary duct atre sia , Byle r 's dise ase , and acute hepatitis due to he patitis B virus infection , activitie s of both fractions are highly elevate d as compare d to healthy childre n or those with chronic viral he patitis . More over , se rum aminopeptidase - M se ems to re ¯ e ct othe r aspe cts of the pathological proce ss than those re ¯ ected by the alanine aminotransfe rase and g - glutamyltranspe ptidase . Due to incre ase d activity and broad substrate speci ® city , the e nzyme se e ms to be also a cofactor of chole stasis and he patitis .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Aim of this study was to de termine and furthe r characte rize the se rum aminope ptidase - M in childre n with live r dise ase s. Based on our ne w assay ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"we have shown two fractions of the e nzyme .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"Activity of the ® rst fraction is e xpre sse d in undilute d se rum at pH adjuste d from 8.5 ( pH of storage d se rum ) to 7.4 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"Activity of the se cond fraction ( cryptic activity ) appe ars in the serum ( pH 7.4 ) as a result of dilution and/or addition of aniline naphthale ne sulfonic acid .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"In childre n with Alagille syndrome ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"e xtrahe patic biliary duct atre sia ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"Byle r 's dise ase ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"and acute hepatitis due to he patitis B virus infection ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"activitie s of both fractions are highly elevate d as compare d to healthy childre n or those with chronic viral he patitis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"More over , se rum aminopeptidase - M se ems to re ¯ e ct othe r aspe cts of the pathological proce ss than those re ¯ ected by the alanine aminotransfe rase and g - glutamyltranspe ptidase .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Due to incre ase d activity and broad substrate speci ® city ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"the e nzyme se e ms to be also a cofactor of chole stasis and he patitis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "3e3c84ba064eb8d3a0f7972d43235da7271478e8", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIn the USA , infectious diseases continue to exact a substantial toll on health and health-care resources . Endemic diseases such as chronic hepatitis , HIV , and other sexually transmitted infections aff ect millions of individuals and widen health disparities . Additional concerns include health-care-associated and foodborne infections-both of which have been targets of broad prevention eff orts , with success in some areas , yet major challenges remain . Although substantial progress in reduction of the burden of vaccine-preventable diseases has been made , continued cases and outbreaks of these diseases persist , driven by various contributing factors . Worldwide , emerging and reemerging infections continue to challenge prevention and control strategies while the growing problem of antimicrobial resistance needs urgent action . An important priority for control of infectious disease is to ensure that scientifi c and technological advances in molecular diagnostics and bioinformatics are well integrated into public health . Broad and diverse partnerships across governments , health care , academia , and industry , and with the public , are essential to eff ectively reduce the burden of infectious diseases .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"In the USA , infectious diseases continue to exact a substantial toll on health and health-care resources .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Endemic diseases such as chronic hepatitis ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"HIV , and other sexually transmitted infections aff ect millions of individuals and widen health disparities .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Additional concerns include health-care-associated and foodborne infections-both of which have been targets of broad prevention eff orts ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"with success in some areas , yet major challenges remain .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Although substantial progress in reduction of the burden of vaccine-preventable diseases has been made ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"continued cases and outbreaks of these diseases persist ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"driven by various contributing factors .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"Worldwide , emerging and reemerging infections continue to challenge prevention and control strategies while the growing problem of antimicrobial resistance needs urgent action .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"An important priority for control of infectious disease is to ensure that scientifi c and technological advances in molecular diagnostics and bioinformatics are well integrated into public health .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Broad and diverse partnerships across governments ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"health care , academia , and industry ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"and with the public , are essential to eff ectively reduce the burden of infectious diseases .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "971775a96494a12f91b70fd4b8ccaa461a5f0f98", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nLigand-receptor interactions are customarily described by equations that apply to solutes . Yet , most receptors are present in cell membranes so that sufficiently lipophilic ligands could reach the receptor by a two-dimensional approach within the membrane . As summarized in this review , this may affect the ligand-receptor interaction in many ways . Biophysicians calculated that , compared to a threedimensional approach from the liquid phase , such approach could alter the time the ligands need to find a receptor . Biochemists found that ligand incorporation in lipid bilayers modifies their conformation . This , along with the depth at which the ligands reside in the bilayer , will affect the probability of successful receptor interaction . Novel mechanisms were also introduced , including `` exosite '' binding and ligand translocation between the receptor 's ␣ - helical transmembrane domains . Pharmacologists focused attention at ligand concentrations in membrane , their adsorption and release rates and the effects thereof on ligand potency and residence time at the receptor . ( G. Vauquelin ) . physics , biochemistry , pharmacology , biology and chemistry have contributed to a better knowledge of how membranes may affect ligand-receptor ( as well as substrate-enzyme ) interactions at the molecular level . The ambition of this review is to integrate the outcomes of these studies in a single comprehensive monograph and , by doing so , to stimulate interdisciplinary cross-talks on this far from obsolete topic .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Ligand-receptor interactions are customarily described by equations that apply to solutes .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Yet , most receptors are present in cell membranes so that sufficiently lipophilic ligands could reach the receptor by a two-dimensional approach within the membrane .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"As summarized in this review ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"this may affect the ligand-receptor interaction in many ways .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Biophysicians calculated that , compared to a threedimensional approach from the liquid phase ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"such approach could alter the time the ligands need to find a receptor .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"Biochemists found that ligand incorporation in lipid bilayers modifies their conformation .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"This , along with the depth at which the ligands reside in the bilayer ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"will affect the probability of successful receptor interaction .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"Novel mechanisms were also introduced ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"including `` exosite '' binding and ligand translocation between the receptor 's ␣ - helical transmembrane domains .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Pharmacologists focused attention at ligand concentrations in membrane ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"their adsorption and release rates and the effects thereof on ligand potency and residence time at the receptor .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 13}, {\"segment_text\": \"( G. Vauquelin ) .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 14}, {\"segment_text\": \"physics , biochemistry , pharmacology ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 15}, {\"segment_text\": \"biology and chemistry have contributed to a better knowledge of how membranes may affect ligand-receptor ( as well as substrate-enzyme ) interactions at the molecular level .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 16}, {\"segment_text\": \"The ambition of this review is to integrate the outcomes of these studies in a single comprehensive monograph and ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"by doing so , to stimulate interdisciplinary cross-talks on this far from obsolete topic .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "b55c993891c702e7ec32d579fd90f380c3814ab9", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCoronaviruses ( CoVs ) are a large group of enveloped viruses with a single-strand RNA genome , which continuously circulate in mammals and birds and pose a threat to livestock , companion animals , and humans . CoVs harboured by avian species are classified to the genera gamma-and deltacoronaviruses . Within the gamma-CoVs the main representative is avian coronavirus , a taxonomic name which includes the highly contagious infectious bronchitis viruses ( IBVs ) in chickens and similar viruses infecting other domestic birds such as turkeys , guinea fowls , or quails . Additionally , IBVs have been detected in healthy wild birds , demonstrating that they may act as the vector between domestic and free-living birds . Moreover , CoVs other than IBVs , are identified in wild birds , which suggests that wild birds play a key role in the epidemiology of other gammaCoVs and deltaCoVs . Development of molecular techniques has significantly improved knowledge of the prevalence of CoVs in avian species . The methods adopted in monitoring studies of CoVs in different avian species are mainly based on detection of conservative regions within the viral replicase , nucleocapsid genes , and 3 ` UTR or 5 ` UTR . The purpose of this review is to summarise recent discoveries in the areas of epidemiology and diagnosis of CoVs in avian species and to understand the role of wild birds in the virus distribution .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Coronaviruses ( CoVs ) are a large group of enveloped viruses with a single-strand RNA genome ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"which continuously circulate in mammals and birds and pose a threat to livestock ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"companion animals , and humans .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"CoVs harboured by avian species are classified to the genera gamma-and deltacoronaviruses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Within the gamma-CoVs the main representative is avian coronavirus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"a taxonomic name which includes the highly contagious infectious bronchitis viruses ( IBVs ) in chickens and similar viruses infecting other domestic birds such as turkeys ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"guinea fowls , or quails .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Additionally , IBVs have been detected in healthy wild birds ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"demonstrating that they may act as the vector between domestic and free-living birds .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"Moreover , CoVs other than IBVs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"are identified in wild birds ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"which suggests that wild birds play a key role in the epidemiology of other gammaCoVs and deltaCoVs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Development of molecular techniques has significantly improved knowledge of the prevalence of CoVs in avian species .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"The methods adopted in monitoring studies of CoVs in different avian species are mainly based on detection of conservative regions within the viral replicase ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"nucleocapsid genes , and 3 ` UTR or 5 ` UTR .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"The purpose of this review is to summarise recent discoveries in the areas of epidemiology and diagnosis of CoVs in avian species and to understand the role of wild birds in the virus distribution .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 16}]}"}]}
{"paper_id": "923eca0b4175d09814a117b685e434c2f93bc25c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe cattle industry is one of the most important Brazilian agribusiness sectors and is a strong contributor to the national economy . Annually about 44.6 million calves are bred , which makes the optimal management of these animals extremely important . Several diseases can affect the initial stages of the bovine production chain , being the bovine respiratory syncytial virus ( BRSV ) one of the most relevant pathogens . This study aimed to characterize the epidemiology of BRSV infection in dairy cattle herds of São Paulo State , Brazil , using serological and risk factors analyses . For that , 1243 blood samples were collected of animals from 26 farms and a questionnaire about possible risk factors for BRSV prevalence was performed . The obtained blood sera were analyzed using virus neutralization test ( VNT ) . Results : VNT results showed high BRSV prevalence in dairy cattle herds , reaching 79.5 % of seropositivity . The BRSV seroprevalence among studied farms ranged from 40 to 100 % . The analysis of risk factors indicated that the age group and the occurrence of coinfection with bovine herpesvirus 1 ( BoHV-1 ) and bovine viral diarrhea virus 1 ( BVDV-1 ) should be associated with a higher prevalence of BRSV , while natural suckling was considered a protective factor . The study showed that adult animals over 1 year old are an important risk factor for the high seroprevalence of BRSV in herds . The high BRSV prevalence associated with BoHV-1 and BVDV-1 suggests that biosecurity measures should be applied in order to reduce viral dissemination . Additionally , the natural suckling may be an important management to protect calves from high BRSV seroprevalence .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The cattle industry is one of the most important Brazilian agribusiness sectors and is a strong contributor to the national economy .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Annually about 44.6 million calves are bred ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"which makes the optimal management of these animals extremely important .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Several diseases can affect the initial stages of the bovine production chain ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"being the bovine respiratory syncytial virus ( BRSV ) one of the most relevant pathogens .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"This study aimed to characterize the epidemiology of BRSV infection in dairy cattle herds of São Paulo State ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"Brazil , using serological and risk factors analyses .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"For that , 1243 blood samples were collected of animals from 26 farms and a questionnaire about possible risk factors for BRSV prevalence was performed .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The obtained blood sera were analyzed using virus neutralization test ( VNT ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Results : VNT results showed high BRSV prevalence in dairy cattle herds ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"reaching 79.5 % of seropositivity .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"The BRSV seroprevalence among studied farms ranged from 40 to 100 % .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"The analysis of risk factors indicated that the age group and the occurrence of coinfection with bovine herpesvirus 1 ( BoHV-1 ) and bovine viral diarrhea virus 1 ( BVDV-1 ) should be associated with a higher prevalence of BRSV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"while natural suckling was considered a protective factor .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"The study showed that adult animals over 1 year old are an important risk factor for the high seroprevalence of BRSV in herds .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"The high BRSV prevalence associated with BoHV-1 and BVDV-1 suggests that biosecurity measures should be applied in order to reduce viral dissemination .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"Additionally , the natural suckling may be an important management to protect calves from high BRSV seroprevalence .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}]}"}]}
{"paper_id": "52dfa9fbd6dcf7c51fac5cb85a88fb154506a722", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nFrom December 2019 , an outbreak of unusual pneumonia was reported in Wuhan with many cases linked to Huanan Seafood Market that sells seafood as well as live exotic animals . We investigated two patients who developed acute respiratory syndromes after independent contact history with this market . The two patients shared common clinical features including fever , cough , and multiple ground-glass opacities in the bilateral lung field with patchy infiltration . Here , we highlight the use of a low-input metagenomic next-generation sequencing ( mNGS ) approach on RNA extracted from bronchoalveolar lavage fluid ( BALF ) . It rapidly identified a novel coronavirus ( named 2019-nCoV according to World Health Organization announcement ) which was the sole pathogens in the sample with very high abundance level ( 1.5 % and 0.62 % of total RNA sequenced ) . The entire viral genome is 29,881 nt in length ( GenBank MN988668 and MN988669 , Sequence Read Archive database Bioproject accession PRJNA601736 ) and is classified into β-coronavirus genus . Phylogenetic analysis indicates that 2019-nCoV is close to coronaviruses ( CoVs ) circulating in Rhinolophus ( Horseshoe bats ) , such as 98.7 % nucleotide identity to partial RdRp gene of bat coronavirus strain BtCoV / 4991 ( GenBank KP876546 , 370 nt sequence of RdRp and lack of other genome sequence ) and 87.9 % nucleotide identity to bat coronavirus strain bat-SL-CoVZC45 and bat-SL-CoVZXC21 . Evolutionary analysis based on ORF1a/1b , S , and N genes also suggests 2019-nCoV is more likely a novel CoV independently introduced from animals to humans .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"From December 2019 , an outbreak of unusual pneumonia was reported in Wuhan with many cases linked to Huanan Seafood Market that sells seafood as well as live exotic animals .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"We investigated two patients who developed acute respiratory syndromes after independent contact history with this market .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"The two patients shared common clinical features including fever ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"cough , and multiple ground-glass opacities in the bilateral lung field with patchy infiltration .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Here , we highlight the use of a low-input metagenomic next-generation sequencing ( mNGS ) approach on RNA extracted from bronchoalveolar lavage fluid ( BALF ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"It rapidly identified a novel coronavirus ( named 2019-nCoV according to World Health Organization announcement ) which was the sole pathogens in the sample with very high abundance level ( 1.5 % and 0.62 % of total RNA sequenced ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"The entire viral genome is 29,881 nt in length ( GenBank MN988668 and MN988669 , Sequence Read Archive database Bioproject accession PRJNA601736 ) and is classified into β-coronavirus genus .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"Phylogenetic analysis indicates that 2019-nCoV is close to coronaviruses ( CoVs ) circulating in Rhinolophus ( Horseshoe bats ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"such as 98.7 % nucleotide identity to partial RdRp gene of bat coronavirus strain BtCoV / 4991 ( GenBank KP876546 , 370 nt sequence of RdRp and lack of other genome sequence ) and 87.9 % nucleotide identity to bat coronavirus strain bat-SL-CoVZC45 and bat-SL-CoVZXC21 .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Evolutionary analysis based on ORF1a/1b ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"S , and N genes also suggests 2019-nCoV is more likely a novel CoV independently introduced from animals to humans .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}]}"}]}
{"paper_id": "3855de3900dee3cecb63982884763c5dac76b8cb", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nViruses assemble large macromolecular repeat structures that become part of the infectious particles or virions . Ribonucleocapsids ( RNCs ) of negative strand RNA viruses are a prime example where repetition of nucleoprotein ( NP ) along the genome creates a core polymeric helical scaffold that accommodates other nucleocapsid proteins including viral polymerase . The RNCs are transported through the cytosol for packaging into virions through association with viral matrix proteins at cell membranes . We hypothesized that RNC would be ideal targets for crosslinkers engineered to promote aberrant protein-protein interactions , thereby blocking their orderly transport and packaging . Previously , we had generated single-domain antibodies ( sdAbs ) against Filoviruses that have all targeted highly conserved C-terminal regions of NP known to be repetitively exposed along the length of the RNCs of Marburgvirus ( MARV ) and Ebolavirus ( EBOV ) . Our crosslinker design consisted of dimeric sdAb expressed intracellularly , which we call Xintrabodies ( X-for crosslinking ) . Electron microscopy of purified NP polymers incubated with purified sdAb constructs showed NP aggregation occurred in a genus-specific manner with dimeric and not monomeric sdAb . A virus-like particle ( VLP ) assay was used for initial evaluation where we found that dimeric sdAb inhibited NP incorporation into VP40-based VLPs whereas monomeric sdAb did not . Inhibition of NP packaging was genus specific . Confocal microscopy revealed dimeric sdAb was diffuse when expressed alone but focused on pools of NP when the two were coexpressed , while monomeric sdAb showed ambivalent partition . Infection of stable Vero cell lines expressing dimeric sdAb specific for either MARV or EBOV NP resulted in smaller plaques and reduced progeny of cognate virus relative to wild-type Vero cells . Though the impact was marginal at later time-points , the collective data suggest that viral replication can be reduced by crosslinking intracellular NP using relatively small amounts of dimeric sdAb to restrict NP packaging . The stoichiometry and ease of application of the approach would likely benefit from transitioning away from intracellular expression of crosslinking sdAb to exogenous delivery of antibody . By retuning sdAb specificity , the approach of crosslinking highly conserved regions of assembly critical proteins may well be applicable to inhibiting replication processes of a broad spectrum of viruses .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Viruses assemble large macromolecular repeat structures that become part of the infectious particles or virions .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Ribonucleocapsids ( RNCs ) of negative strand RNA viruses are a prime example where repetition of nucleoprotein ( NP ) along the genome creates a core polymeric helical scaffold that accommodates other nucleocapsid proteins including viral polymerase .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The RNCs are transported through the cytosol for packaging into virions through association with viral matrix proteins at cell membranes .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"We hypothesized that RNC would be ideal targets for crosslinkers engineered to promote aberrant protein-protein interactions ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"thereby blocking their orderly transport and packaging .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Previously , we had generated single-domain antibodies ( sdAbs ) against Filoviruses that have all targeted highly conserved C-terminal regions of NP known to be repetitively exposed along the length of the RNCs of Marburgvirus ( MARV ) and Ebolavirus ( EBOV ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"Our crosslinker design consisted of dimeric sdAb expressed intracellularly ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"which we call Xintrabodies ( X-for crosslinking ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Electron microscopy of purified NP polymers incubated with purified sdAb constructs showed NP aggregation occurred in a genus-specific manner with dimeric and not monomeric sdAb .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"A virus-like particle ( VLP ) assay was used for initial evaluation where we found that dimeric sdAb inhibited NP incorporation into VP40-based VLPs whereas monomeric sdAb did not .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Inhibition of NP packaging was genus specific .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Confocal microscopy revealed dimeric sdAb was diffuse when expressed alone but focused on pools of NP when the two were coexpressed ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"while monomeric sdAb showed ambivalent partition .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Infection of stable Vero cell lines expressing dimeric sdAb specific for either MARV or EBOV NP resulted in smaller plaques and reduced progeny of cognate virus relative to wild-type Vero cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Though the impact was marginal at later time-points ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"the collective data suggest that viral replication can be reduced by crosslinking intracellular NP using relatively small amounts of dimeric sdAb to restrict NP packaging .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"The stoichiometry and ease of application of the approach would likely benefit from transitioning away from intracellular expression of crosslinking sdAb to exogenous delivery of antibody .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"By retuning sdAb specificity , the approach of crosslinking highly conserved regions of assembly critical proteins may well be applicable to inhibiting replication processes of a broad spectrum of viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "75882d6856d4243248aa32fe119153efeb0dbe12", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCitation MacParland SA , Ma X-Z , Chen L , Khattar R , Cherepanov V , Selzner M , Feld JJ , Selzner N , McGilvray ID . 2016 . Lipopolysaccharide and tumor necrosis factor alpha inhibit interferon signaling in hepatocytes by increasing ubiquitin-like protease 18 ( USP18 ) expression . J Virol 90:5549 -5560 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Citation MacParland SA , Ma X-Z ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 1}, {\"segment_text\": \"Chen L , Khattar R ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 2}, {\"segment_text\": \"Cherepanov V , Selzner M ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 3}, {\"segment_text\": \"Feld JJ , Selzner N , McGilvray ID .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 4}, {\"segment_text\": \"2016 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 5}, {\"segment_text\": \"Lipopolysaccharide and tumor necrosis factor alpha inhibit interferon signaling in hepatocytes by increasing ubiquitin-like protease 18 ( USP18 ) expression .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"J Virol 90:5549 -5560 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 7}]}"}]}
{"paper_id": "bc343b504f04146857602c5800c99ab7d08162d1", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Upper respiratory tract infections ( URTIs ) , including rhinitis , nasopharyngitis , tonsillitis and otitis media ( OM ) , comprise of 88 % of total respiratory infections , especially in children . Therefore effective prevention and treatment of RTIs remain a high priority worldwide . Preclinical and clinical data highlight the rationale for the use and effectiveness of immunity-targeted approaches , including targeted immunisations and nonspecific immunomodulation in the prevention and management of recurrent upper RTIs . The idea of this review was to summarise the current evidence and address key questions concerning the use of conservative and immunity-targeted approaches to recurrent and chronic URTIs , with a focus on the paediatric population . Health Source : Nursing/Academic Edition ; MEDLINE ; clinicaltrials.gov ; and Cochrane databases . In total , 84 articles were retrieved and reviewed . Two independent researchers focused on primary and secondary endpoints in systematic reviews , metaanalyses and randomised , controlled trials , using immunity-directed strategies as the control group or within a subpopulation of larger studies . Existing guidelines and interventional/observational studies on novel applications were also included . Results : Children are particularly susceptible to RTIs due to the relative immaturity of their immune systems , as well as other potential predisposing factors such as day care attendance and/or toxic environmental factors ( eg increased pathogenic microbial exposure and air pollutants ) . Recurrent URTIs can affect otherwise healthy children , leading to clinical sequelae and complications , including the development of chronic conditions or the need for surgery . Available pre-clinical and clinical data highlight the rationale for the use and effectiveness of immunity-targeted approaches , including targeted immunisations ( flu and pneumococcal vaccines ) and non-specific immunomodulation ( bacterial lysates ) , in the prevention and management of recurrent croup , tonsillitis , otitis media , recurrent acute rhinosinusitis and chronic rhinosinusitis . In this review , we summarise the current evidence and provide data demonstrating that some immunity-targeted strategies , including vaccination and immunomodulation , have proved effective in the treatment and prevention of recurrent and chronic URTIs in children . FELESZKO Et aL. .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Upper respiratory tract infections ( URTIs ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"including rhinitis , nasopharyngitis , tonsillitis and otitis media ( OM ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"comprise of 88 % of total respiratory infections , especially in children .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Therefore effective prevention and treatment of RTIs remain a high priority worldwide .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Preclinical and clinical data highlight the rationale for the use and effectiveness of immunity-targeted approaches ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"including targeted immunisations and nonspecific immunomodulation in the prevention and management of recurrent upper RTIs .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"The idea of this review was to summarise the current evidence and address key questions concerning the use of conservative and immunity-targeted approaches to recurrent and chronic URTIs ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"with a focus on the paediatric population .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"Health Source : Nursing/Academic Edition ; MEDLINE ; clinicaltrials.gov ; and Cochrane databases .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"In total , 84 articles were retrieved and reviewed .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Two independent researchers focused on primary and secondary endpoints in systematic reviews ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"metaanalyses and randomised , controlled trials ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"using immunity-directed strategies as the control group or within a subpopulation of larger studies .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"Existing guidelines and interventional/observational studies on novel applications were also included .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"Results : Children are particularly susceptible to RTIs due to the relative immaturity of their immune systems ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"as well as other potential predisposing factors such as day care attendance and/or toxic environmental factors ( eg increased pathogenic microbial exposure and air pollutants ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"Recurrent URTIs can affect otherwise healthy children ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"leading to clinical sequelae and complications ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"including the development of chronic conditions or the need for surgery .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"Available pre-clinical and clinical data highlight the rationale for the use and effectiveness of immunity-targeted approaches ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}, {\"segment_text\": \"including targeted immunisations ( flu and pneumococcal vaccines ) and non-specific immunomodulation ( bacterial lysates ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}, {\"segment_text\": \"in the prevention and management of recurrent croup ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 22}, {\"segment_text\": \"tonsillitis , otitis media , recurrent acute rhinosinusitis and chronic rhinosinusitis .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 23}, {\"segment_text\": \"In this review , we summarise the current evidence and provide data demonstrating that some immunity-targeted strategies ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 24}, {\"segment_text\": \"including vaccination and immunomodulation , have proved effective in the treatment and prevention of recurrent and chronic URTIs in children .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 25}, {\"segment_text\": \"FELESZKO Et aL. .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 26}]}"}]}
{"paper_id": "8a541d5535412574cecb9a7bf5489e569896d15c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe objective of the present study was to evaluate the protective effect of humoral and cellular immunities on turkeys infected with turkey coronavirus ( TCV ) . Two trials were conducted with two separate hatches of turkey poults . Turkeys were experimentally immunosuppressed with cyclosporin A ( CsA ) or cyclophosphamide ( CY ) and infected with TCV . Prior to infection , treatment with CsA selectively suppressed T cell activity as revealed by 2 ± 3 fold decreased p , 0:1 lymphocyte proliferation responses to a T cell mitogen , concanavalin A ( Con A ) . Treatment with CY mainly induced B cell de ® ciency as indicated by signi ® cant reductions p , 0:05 in antibody responses to sheep erythrocytes 7 days after injection . Body weight gain of turkeys treated with CY was signi ® cantly lower p , 0:05 than that of untreated turkeys at 9 days post-infection ( PI ) . Turkeys treated with CY had 1 ± 2 fold higher immuno ¯ uorescent antibody assay ( IFA ) scores for TCV antigens p , 0:05 in the intestine than untreated turkeys at 9 or 14 days PI . These results suggested that humoral immunity against TCV infection may be important in turkeys . q\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The objective of the present study was to evaluate the protective effect of humoral and cellular immunities on turkeys infected with turkey coronavirus ( TCV ) .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Two trials were conducted with two separate hatches of turkey poults .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"Turkeys were experimentally immunosuppressed with cyclosporin A ( CsA ) or cyclophosphamide ( CY ) and infected with TCV .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Prior to infection , treatment with CsA selectively suppressed T cell activity as revealed by 2 ± 3 fold decreased p ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"0:1 lymphocyte proliferation responses to a T cell mitogen ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"concanavalin A ( Con A ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Treatment with CY mainly induced B cell de ® ciency as indicated by signi ® cant reductions p ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"0:05 in antibody responses to sheep erythrocytes 7 days after injection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Body weight gain of turkeys treated with CY was signi ® cantly lower p ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"0:05 than that of untreated turkeys at 9 days post-infection ( PI ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Turkeys treated with CY had 1 ± 2 fold higher immuno ¯ uorescent antibody assay ( IFA ) scores for TCV antigens p ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"0:05 in the intestine than untreated turkeys at 9 or 14 days PI .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"These results suggested that humoral immunity against TCV infection may be important in turkeys .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"q\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 14}]}"}]}
{"paper_id": "8fa6afa0af58592ae93e47e90d84f7e064c36fdc", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nLittle red flying fox ( Pteropus scapulatus ) Morphology PCR 18S ribosomal RNA ( rRNA ) Glycosomal glyceraldehyde phosphate dehydrogenase ( gGAPDH ) Phylogeny Little is known about the genetic diversity and pathogenicity of trypanosomes in Australian bats . Recently a novel trypanosome species was identified in an adult female little red flying fox ( Pteropus scapulatus ) with clinical and pathological evidence of trypanosomosis . The present study used morphology and molecular methods to demonstrate that this trypanosome is a distinct species and we propose the name Trypanosoma teixeirae sp. n. Morphological comparison showed that its circulating trypomastigotes were significantly different from those of Trypanosoma pteropi and Trypanosoma hipposideri , two species previously described from Australian bats . Genetic information was not available for T. pteropi and T. hipposideri but phylogenetic analyses at the 18S ribosomal RNA ( rRNA ) and glycosomal glyceraldehyde phosphate dehydrogenase ( gGAPDH ) loci indicated that T. teixeirae sp. n. was genetically distinct and clustered with other bat-derived trypanosome species within the Trypanosoma cruzi clade .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Little red flying fox ( Pteropus scapulatus ) Morphology PCR 18S ribosomal RNA ( rRNA ) Glycosomal glyceraldehyde phosphate dehydrogenase ( gGAPDH ) Phylogeny\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Little is known about the genetic diversity and pathogenicity of trypanosomes in Australian bats .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Recently a novel trypanosome species was identified in an adult female little red flying fox ( Pteropus scapulatus ) with clinical and pathological evidence of trypanosomosis .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The present study used morphology and molecular methods to demonstrate that this trypanosome is a distinct species and we propose the name Trypanosoma teixeirae sp. n. Morphological comparison showed that its circulating trypomastigotes were significantly different from those of Trypanosoma pteropi and Trypanosoma hipposideri ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"two species previously described from Australian bats .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Genetic information was not available for T. pteropi and T. hipposideri but phylogenetic analyses at the 18S ribosomal RNA ( rRNA ) and glycosomal glyceraldehyde phosphate dehydrogenase ( gGAPDH ) loci indicated that T. teixeirae sp. n. was genetically distinct and clustered with other bat-derived trypanosome species within the Trypanosoma cruzi clade .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}]}"}]}
{"paper_id": "a0e3172470d98c87c861e16493640155c2f9c401", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\n( ` filoviruses ' ) that cause severe hemorrhagic fever with human case fatality rates of up to 90 % . Filovirus infection requires fusion of the host cell and virus membranes , a process that is mediated by the envelope glycoprotein ( GP ) . GP contains two subunits , the surface subunit ( GP1 ) , which is responsible for cell attachment , and the transmembrane subunit ( GP2 ) , which catalyzes membrane fusion . The GP2 ectodomain contains two heptad repeat regions , N-terminal and C-terminal ( NHR and CHR , respectively ) that adopt a six-helix bundle during the fusion process . The refolding of this six-helix bundle provides the thermodynamic driving force to overcome barriers associated with membrane fusion . Here we report the crystal structure of the MARV GP2 core domain in its post-fusion ( six-helix bundle ) conformation at 1.9 Å resolution . The MARV GP2 core domain backbone conformation is virtually identical to that of EBOV GP2 ( reported previously ) , and consists of a central NHR core trimeric coiled-coil packed against peripheral CHR α-helices and an intervening loop/helix-turn-helix segment . We previously reported that the stability of the MARV GP2 post-fusion structure is highly pH-dependent , with increasing stability at lower pH ( Harrison , J.S. ; Koellhoffer , J. K. ; Chandran , K. ; and Lai , J. R. Biochemistry , 2012Biochemistry , , 51 , 2515Biochemistry , -2525 . We hypothesized that this pH-dependent stability provides a mechanism for conformational control such that the post-fusion six helix bundle is promoted in the environments of appropriately matured endosomes . In this report , a structural rationale for this pH-dependent stability is described , and involves a high-density array of core and surface acidic side chains at the midsection of the structure , termed the ` anion stripe . ' In addition , many surface-exposed salt bridges likely contribute to stabilizing the post-fusion structure at low pH. These results provide structural insights into the mechanism of MARV GP2-mediated membrane fusion .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"( ` filoviruses ' ) that cause severe hemorrhagic fever with human case fatality rates of up to 90 % .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Filovirus infection requires fusion of the host cell and virus membranes ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"a process that is mediated by the envelope glycoprotein ( GP ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"GP contains two subunits , the surface subunit ( GP1 ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"which is responsible for cell attachment ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"and the transmembrane subunit ( GP2 ) , which catalyzes membrane fusion .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"The GP2 ectodomain contains two heptad repeat regions ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"N-terminal and C-terminal ( NHR and CHR , respectively ) that adopt a six-helix bundle during the fusion process .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"The refolding of this six-helix bundle provides the thermodynamic driving force to overcome barriers associated with membrane fusion .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"Here we report the crystal structure of the MARV GP2 core domain in its post-fusion ( six-helix bundle ) conformation at 1.9 Å resolution .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The MARV GP2 core domain backbone conformation is virtually identical to that of EBOV GP2 ( reported previously ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and consists of a central NHR core trimeric coiled-coil packed against peripheral CHR α-helices and an intervening loop/helix-turn-helix segment .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"We previously reported that the stability of the MARV GP2 post-fusion structure is highly pH-dependent ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"with increasing stability at lower pH ( Harrison , J.S. ; Koellhoffer , J. K. ; Chandran , K. ; and Lai , J. R. Biochemistry , 2012Biochemistry , , 51 , 2515Biochemistry , -2525 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"We hypothesized that this pH-dependent stability provides a mechanism for conformational control such that the post-fusion six helix bundle is promoted in the environments of appropriately matured endosomes .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"In this report , a structural rationale for this pH-dependent stability is described ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"and involves a high-density array of core and surface acidic side chains at the midsection of the structure ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"termed the ` anion stripe . '\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"In addition , many surface-exposed salt bridges likely contribute to stabilizing the post-fusion structure at low pH. These results provide structural insights into the mechanism of MARV GP2-mediated membrane fusion .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}]}"}]}
{"paper_id": "6d03f3e2dd6554f15526cb089337fa592fb1834c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAnnotation of the genome sequence of the SARS-CoV ( severe acute respiratory syndrome-associated coronavirus ) is indispensable to understand its evolution and pathogenesis . We have performed a full annotation of the SARS-CoV genome sequences by using annotation programs publicly available or developed by ourselves . Totally , 21 open reading frames ( ORFs ) of genes or putative uncharacterized proteins ( PUPs ) were predicted . Seven PUPs had not been reported previously , and two of them were predicted to contain transmembrane regions . Eight ORFs partially overlapped with or embedded into those of known genes , revealing that the SARS-CoV genome is a small and compact one with overlapped coding regions . The most striking discovery is that an ORF locates on the minus strand . We have also annotated non-coding regions and identified the transcription regulating sequences ( TRS ) in the intergenic regions . The analysis of TRS supports the minus strand extending transcription mechanism of coronavirus . The SNP analysis of different isolates reveals that mutations of the sequences do not affect the prediction results of ORFs .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Annotation of the genome sequence of the SARS-CoV ( severe acute respiratory syndrome-associated coronavirus ) is indispensable to understand its evolution and pathogenesis .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"We have performed a full annotation of the SARS-CoV genome sequences by using annotation programs publicly available or developed by ourselves .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"Totally , 21 open reading frames ( ORFs ) of genes or putative uncharacterized proteins ( PUPs ) were predicted .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"Seven PUPs had not been reported previously ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"and two of them were predicted to contain transmembrane regions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Eight ORFs partially overlapped with or embedded into those of known genes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"revealing that the SARS-CoV genome is a small and compact one with overlapped coding regions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"The most striking discovery is that an ORF locates on the minus strand .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"We have also annotated non-coding regions and identified the transcription regulating sequences ( TRS ) in the intergenic regions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"The analysis of TRS supports the minus strand extending transcription mechanism of coronavirus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The SNP analysis of different isolates reveals that mutations of the sequences do not affect the prediction results of ORFs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}]}"}]}
{"paper_id": "79ffac5ab7acd3c43a3e0866ed150fea9a0ec1c8", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPurpose : Malignant melanoma 's ( MM ) incidence is rising faster than that of any other cancer in the US and the overall survival at 5 years is less than 10 % . B cell associated protein 31 ( BAP31 ) is overexpressed in most MMs and might be a promising target for immunotherapy of this disease . Experimental design : Firstly , we investigated the expression profiles of human BAP31 ( hBAP31 ) and mouse BAP31 ( mBAP31 ) in human and mouse normal tissues , respectively . The expression level of hBAP31 in human MMs and mBAP31 in B16 melanoma cells was also analyzed . Then we constructed novel mBAP31 DNA vaccines and tested there ability to stimulate mBAP31-specific immune responses and antitumor immunity in B16 melanoma-bearing mice . Results : For the first time , we found that protein expression of hBAP31 were dramatically upregulated in human MMs when compared with human normal tissues . Predominant protein expression of mBAP31 was found in mouse B16 melanoma cells but not in mouse important organs . When mice were immunized with mBAP31 DNA vaccines , strong cellular response to mBAP31 was observed in the vaccinated mice . CTLs isolated from immunized mice could effectively kill mBAP31-positive target mouse B16 melanoma tumor cells in vitro and vaccination with mBAP31 DNA vaccines had potent anti-tumor activity in therapeutic model using B16 melanoma cells . Conclusions : These are the first data supporting a vaccine targeting BAP31 that is capable of inducing effective immunity against BAP31-expressing MMs and will be applicable to human MMs and hBAP31 DNA vaccine warrants investigation in human clinical trials .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Purpose : Malignant melanoma 's ( MM ) incidence is rising faster than that of any other cancer in the US and the overall survival at 5 years is less than 10 % .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"B cell associated protein 31 ( BAP31 ) is overexpressed in most MMs and might be a promising target for immunotherapy of this disease .\", \"label\": \"purpose\", \"decision_reference\": \"boundary background_vs_purpose\", \"id\": 2}, {\"segment_text\": \"Experimental design : Firstly , we investigated the expression profiles of human BAP31 ( hBAP31 ) and mouse BAP31 ( mBAP31 ) in human and mouse normal tissues , respectively .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"The expression level of hBAP31 in human MMs and mBAP31 in B16 melanoma cells was also analyzed .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Then we constructed novel mBAP31 DNA vaccines and tested there ability to stimulate mBAP31-specific immune responses and antitumor immunity in B16 melanoma-bearing mice .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Results : For the first time ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"we found that protein expression of hBAP31 were dramatically upregulated in human MMs when compared with human normal tissues .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Predominant protein expression of mBAP31 was found in mouse B16 melanoma cells but not in mouse important organs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"When mice were immunized with mBAP31 DNA vaccines ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"strong cellular response to mBAP31 was observed in the vaccinated mice .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"CTLs isolated from immunized mice could effectively kill mBAP31-positive target mouse B16 melanoma tumor cells in vitro and vaccination with mBAP31 DNA vaccines had potent anti-tumor activity in therapeutic model using B16 melanoma cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Conclusions : These are the first data supporting a vaccine targeting BAP31 that is capable of inducing effective immunity against BAP31-expressing MMs and will be applicable to human MMs and hBAP31 DNA vaccine warrants investigation in human clinical trials .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}]}"}]}
{"paper_id": "1b58422e266ab9339c919119923229d080f27360", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nObjective : Pleural effusion is common problem , but the rapid and reliable diagnosis for specific pathogenic effusions are lacking . This study aimed to identify the diagnosis based on clinical variables to differentiate pleural tuberculous exudates from other pleural effusions . We also investigated the role of renin-angiotensin system ( RAS ) and matrix metalloproteinase ( MMPs ) in the pathogenesis of pleural exudates . Experimental design : The major components in RAS and extracellular matrix metabolism , including angiotensin converting enzyme ( ACE ) , ACE2 , MMP-2 and MMP-9 activities , were measured and compared in the patients with transudative ( n = 45 ) and exudative ( n = 80 ) effusions . The exudative effusions were come from the patients with tuberculosis ( n = 20 ) , pneumonia ( n = 32 ) , and adenocarcinoma ( n = 28 ) . Results : Increased ACE and equivalent ACE2 activities , resulting in a significantly increased ACE/ACE2 ratio in exudates , were detected compared to these values in transudates . MMP-9 activity in exudates was significantly higher than that in transudates . The significant correlation between ACE and ACE2 activity that was found in transudates was not found in exudates . Advanced analyses showed significantly increased ACE and MMP-9 activities , and decreased ACE2 activity in tuberculous pleural effusions compared with those in pneumonia and adenocarcinoma effusions . The results indicate that increased ACE and MMP-9 activities found in the exudates were mainly contributed from a higher level of both enzyme activities in the tuberculous pleural effusions . Conclusion : Interplay between ACE and ACE2 , essential functions in the RAS , and abnormal regulation of MMP-9 probably play a pivotal role in the development of exudative effusions . Moreover , the ACE/ACE2 ratio combined with MMP-9 activity in pleural fluid may be potential biomarkers for diagnosing tuberculous pleurisy .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Objective : Pleural effusion is common problem ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"but the rapid and reliable diagnosis for specific pathogenic effusions are lacking .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"This study aimed to identify the diagnosis based on clinical variables to differentiate pleural tuberculous exudates from other pleural effusions .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"We also investigated the role of renin-angiotensin system ( RAS ) and matrix metalloproteinase ( MMPs ) in the pathogenesis of pleural exudates .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Experimental design : The major components in RAS and extracellular matrix metabolism ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"including angiotensin converting enzyme ( ACE ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"ACE2 , MMP-2 and MMP-9 activities ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"were measured and compared in the patients with transudative ( n = 45 ) and exudative ( n = 80 ) effusions .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The exudative effusions were come from the patients with tuberculosis ( n = 20 ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"pneumonia ( n = 32 ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"and adenocarcinoma ( n = 28 ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Results : Increased ACE and equivalent ACE2 activities ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"resulting in a significantly increased ACE/ACE2 ratio in exudates ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"were detected compared to these values in transudates .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"MMP-9 activity in exudates was significantly higher than that in transudates .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"The significant correlation between ACE and ACE2 activity that was found in transudates was not found in exudates .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Advanced analyses showed significantly increased ACE and MMP-9 activities ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"and decreased ACE2 activity in tuberculous pleural effusions compared with those in pneumonia and adenocarcinoma effusions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"The results indicate that increased ACE and MMP-9 activities found in the exudates were mainly contributed from a higher level of both enzyme activities in the tuberculous pleural effusions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Conclusion : Interplay between ACE and ACE2 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"essential functions in the RAS ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"and abnormal regulation of MMP-9 probably play a pivotal role in the development of exudative effusions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"Moreover , the ACE/ACE2 ratio combined with MMP-9 activity in pleural fluid may be potential biomarkers for diagnosing tuberculous pleurisy .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}]}"}]}
{"paper_id": "6085ea96b3a7c381215ba90b26f8664ae7c63178", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe full-length genome sequence of a novel swine acute diarrhea syndrome coronavirus ( SADS-CoV ) , CH/FJWT/2018 , was determined , which was genetically most closely related to CN/GDWT/2017 , recently discovered in Fujian , China . The indel sites of the spike ( S ) gene of CH/FJWT/2018 were most similar to those of bat-origin SADS-related coronaviruses .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The full-length genome sequence of a novel swine acute diarrhea syndrome coronavirus ( SADS-CoV ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"CH/FJWT/2018 , was determined , which was genetically most closely related to CN/GDWT/2017 ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"recently discovered in Fujian , China .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"The indel sites of the spike ( S ) gene of CH/FJWT/2018 were most similar to those of bat-origin SADS-related coronaviruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}]}"}]}
{"paper_id": "3d312c9f713033279497546e55cd79f510fe56b7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAim-To examine , among hospital employees exposed to an outbreak of severe acute respiratory syndrome ( SARS ) , post-outbreak levels of depressive symptoms , and the relationship between those depressive symptom levels and the types of outbreak event exposures experienced . 2006 , randomly selected employees ( n = 549 ) of a hospital in Beijing were surveyed concerning their exposures to the city 's 2003 SARS outbreak , and the ways in which the outbreak had affected their mental health . Subjects were assessed on sociodemographic factors , on types of exposure to the outbreak , and on symptoms of post-traumatic stress disorder ( PTSD ) and depression . Results-The results of multinomial regression analyses showed that , with other relevant factors controlled for , being single , having been quarantined during the outbreak , having been exposed to other traumatic events prior to SARS , and perceived SARS-related risk level during the outbreak were found to increase the odds of having a high level of depressive symptoms three years later . Altruistic acceptance of risk during the outbreak was found to decrease the odds of high postoutbreak depressive symptom levels . Conclusions-Policy makers and mental health professionals working to prepare for potential disease outbreaks should be aware that the experience of being quarantined can , in some cases , lead to long-term adverse mental health consequences .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Aim-To examine , among hospital employees exposed to an outbreak of severe acute respiratory syndrome ( SARS ) ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"post-outbreak levels of depressive symptoms ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"and the relationship between those depressive symptom levels and the types of outbreak event exposures experienced .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"2006 , randomly selected employees ( n = 549 ) of a hospital in Beijing were surveyed concerning their exposures to the city 's 2003 SARS outbreak ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"and the ways in which the outbreak had affected their mental health .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Subjects were assessed on sociodemographic factors ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"on types of exposure to the outbreak ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"and on symptoms of post-traumatic stress disorder ( PTSD ) and depression .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Results-The results of multinomial regression analyses showed that ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"with other relevant factors controlled for ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"being single , having been quarantined during the outbreak ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"having been exposed to other traumatic events prior to SARS ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"and perceived SARS-related risk level during the outbreak were found to increase the odds of having a high level of depressive symptoms three years later .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Altruistic acceptance of risk during the outbreak was found to decrease the odds of high postoutbreak depressive symptom levels .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Conclusions-Policy makers and mental health professionals working to prepare for potential disease outbreaks should be aware that the experience of being quarantined can ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"in some cases , lead to long-term adverse mental health consequences .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "4d8552ea8d94977e2a7968a9e7e8ba178f3d44fc", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe objective of this communication is to introduce a conceptual framework for a study that applies a rigorous systems approach to rural disaster preparedness and planning . System Dynamics is a well-established computer-based simulation modeling methodology for analyzing complex social systems that are difficult to change and predict . This approach has been applied for decades to a wide variety of issues of healthcare and other types of service capacity and delivery , and more recently , to some issues of disaster planning and mitigation . The study will use the System Dynamics approach to create computer simulation models as `` what-if '' tools for disaster preparedness planners . We have recently applied the approach to the issue of hospital surge capacity , and have reached some preliminary conclusions - for example , on the question of where in the hospital to place supplementary nursing staff during a severe infectious disease outbreak - some of which we had not expected . Other hospital disaster preparedness issues well suited to System Dynamics analysis include sustaining employee competence and reducing turnover , coordination of medical care and public health resources , and hospital coordination with the wider community to address mass casualties . The approach may also be applied to preparedness issues for agencies other than hospitals , and could help to improve the interactions among all agencies represented in a community 's local emergency planning committee . The simulation models will support an evidence-based approach to rural disaster planning , helping to tie empirical data to decision-making . Disaster planners will be able to simulate a wide variety of scenarios , learn responses to each and develop principles or best practices that apply to a broad spectrum of disaster scenarios . These skills and insights would improve public health practice and be of particular use in the promotion of injury and disease prevention programs and practices . r\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The objective of this communication is to introduce a conceptual framework for a study that applies a rigorous systems approach to rural disaster preparedness and planning .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"System Dynamics is a well-established computer-based simulation modeling methodology for analyzing complex social systems that are difficult to change and predict .\", \"label\": \"purpose\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"This approach has been applied for decades to a wide variety of issues of healthcare and other types of service capacity and delivery ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"and more recently , to some issues of disaster planning and mitigation .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"The study will use the System Dynamics approach to create computer simulation models as `` what-if '' tools for disaster preparedness planners .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"We have recently applied the approach to the issue of hospital surge capacity ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"and have reached some preliminary conclusions - for example ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"on the question of where in the hospital to place supplementary nursing staff during a severe infectious disease outbreak - some of which we had not expected .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Other hospital disaster preparedness issues well suited to System Dynamics analysis include sustaining employee competence and reducing turnover ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"coordination of medical care and public health resources ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"and hospital coordination with the wider community to address mass casualties .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"The approach may also be applied to preparedness issues for agencies other than hospitals ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"and could help to improve the interactions among all agencies represented in a community 's local emergency planning committee .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"The simulation models will support an evidence-based approach to rural disaster planning ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"helping to tie empirical data to decision-making .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"Disaster planners will be able to simulate a wide variety of scenarios ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"learn responses to each and develop principles or best practices that apply to a broad spectrum of disaster scenarios .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"These skills and insights would improve public health practice and be of particular use in the promotion of injury and disease prevention programs and practices .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"r\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 19}]}"}]}
{"paper_id": "58f68e82f134cf3549778fca86251ee61975b596", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Embryonated chicken eggs have been used since the mid-20th century to grow a wide range of animal viruses to high titers . However , eggs have found so far only limited use in the production of recombinant proteins . We now describe a system , based on a Sendai virus minigenome , to produce large amounts of heterologous viral glycoproteins in the allantoic cavity of embryonated eggs . Results : Soluble forms of human respiratory syncytial virus ( HRSV ) and human metapneumovirus ( HMPV ) fusion ( F ) proteins , devoid of their transmembrane and cytoplasmic domains , were produced in allantoic fluids using the Sendai minigenome system . The first step was rescuing in cell cultures Sendai virus minigenomes encoding the proteins of interest , with the help of wild type Sendai virus . The second step was propagating such recombinant defective viruses , together with the helper virus , in the allantoic cavity of chicken embryonated eggs , and passage to optimize protein production . When compared with the production of the same proteins in the culture supernatant of cells infected with vaccinia recombinants , the yield in the allantoic fluid was 5-10 fold higher . Mutant forms of these soluble proteins were easily constructed by site-directed mutagenesis and expressed in eggs using the same approach . The simplicity and economy of the Sendai minigenome system , together with the high yield achieved in the allantoic fluid of eggs , makes it an attractive method to express soluble glycoproteins aimed for structural studies .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Embryonated chicken eggs have been used since the mid-20th century to grow a wide range of animal viruses to high titers .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"However , eggs have found so far only limited use in the production of recombinant proteins .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"We now describe a system ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"based on a Sendai virus minigenome ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"to produce large amounts of heterologous viral glycoproteins in the allantoic cavity of embryonated eggs .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Results : Soluble forms of human respiratory syncytial virus ( HRSV ) and human metapneumovirus ( HMPV ) fusion ( F ) proteins ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"devoid of their transmembrane and cytoplasmic domains ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"were produced in allantoic fluids using the Sendai minigenome system .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"The first step was rescuing in cell cultures Sendai virus minigenomes encoding the proteins of interest ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"with the help of wild type Sendai virus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The second step was propagating such recombinant defective viruses ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"together with the helper virus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"in the allantoic cavity of chicken embryonated eggs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"and passage to optimize protein production .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"When compared with the production of the same proteins in the culture supernatant of cells infected with vaccinia recombinants ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"the yield in the allantoic fluid was 5-10 fold higher .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Mutant forms of these soluble proteins were easily constructed by site-directed mutagenesis and expressed in eggs using the same approach .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"The simplicity and economy of the Sendai minigenome system ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"together with the high yield achieved in the allantoic fluid of eggs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"makes it an attractive method to express soluble glycoproteins aimed for structural studies .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}]}"}]}
{"paper_id": "c1be462ac7a21ad2a0c5c0737a3b71d1af972411", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCultures of an isolate of Penicillium verrucosum var . cyclopium , obtained from stored maize in an area of Balkan ( endemic ) nephro-pathy -- Vratza , Bulgaria -- has consistently induced renal tubular lesions when force-fed to rats for 20 days . The lesions , confined to the lower reaches of the proximal convoluted tubules ( pars recta and junctional zone ) , closely resemble the tubular changes in patients with Balkan nephropathy . Preliminary evidence suggests that this nephrotoxin-producing strain of P. verrucosum var . cyclopium may be implicated in the & aelig ; tiology of Balkan nephropathy .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Cultures of an isolate of Penicillium verrucosum var .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"cyclopium , obtained from stored maize in an area of Balkan ( endemic ) nephro-pathy -- Vratza ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Bulgaria -- has consistently induced renal tubular lesions when force-fed to rats for 20 days .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The lesions , confined to the lower reaches of the proximal convoluted tubules ( pars recta and junctional zone ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 4}, {\"segment_text\": \"closely resemble the tubular changes in patients with Balkan nephropathy .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"Preliminary evidence suggests that this nephrotoxin-producing strain of P. verrucosum var .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"cyclopium may be implicated in the & aelig ; tiology of Balkan nephropathy .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}]}"}]}
{"paper_id": "72f80b98d15a0f4fd1e27bbddd82df2de8297bfa", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nData visualization is an important tool for exploring and communicating findings in medical research , and specially in epidemiological surveillance . The COVID19-Tracker app systematically produces daily updated data visualization and analysis of SARS-CoV-2 epidemic in Spain . It collects automatically daily data on COVID-19 diagnosed cases , intensive care unit admissions , and mortality , from February 24 th , 2020 onwards . Two applications have already been developed ; 1 ) to analyze data trends and estimating short-term projections ; and 2 ) To assess the effect of the lockdown on the trend of incident data . We are currently planning to improve the app by uploading shortly new applications for data visualization and analysis , which may help for a better understanding of the SARS-CoV-2 epidemic data in Spain .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Data visualization is an important tool for exploring and communicating findings in medical research ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"and specially in epidemiological surveillance .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The COVID19-Tracker app systematically produces daily updated data visualization and analysis of SARS-CoV-2 epidemic in Spain .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"It collects automatically daily data on COVID-19 diagnosed cases ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"intensive care unit admissions , and mortality ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"from February 24 th , 2020 onwards .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Two applications have already been developed ; 1 ) to analyze data trends and estimating short-term projections ; and 2 ) To assess the effect of the lockdown on the trend of incident data .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"We are currently planning to improve the app by uploading shortly new applications for data visualization and analysis ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"which may help for a better understanding of the SARS-CoV-2 epidemic data in Spain .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}]}"}]}
{"paper_id": "eb4ea7245691cd679aa73cb84050826db5531394", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\ntime and the number of cycles of H 2 O 2 . This is especially important for inner parts of medical equipment that can not be ventilated during the decontamination process .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"time and the number of cycles of H 2 O 2 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"This is especially important for inner parts of medical equipment that can not be ventilated during the decontamination process .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 2}]}"}]}
{"paper_id": "4cdea155c61583c70e149a95f460306eed5ed923", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe complex antiviral immune mechanisms involve both adaptive and innate reactions mediated by cd T lymphocytes , whose unique immunosurveillance contributions are analyzed here in different clinical and experimental settings . It is beyond any doubt that the fast , potent , cytotoxic as well as non-cytolytic antiviral activities of cd T cells are critical in protecting the host against diverse viral pathogens .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The complex antiviral immune mechanisms involve both adaptive and innate reactions mediated by cd T lymphocytes ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"whose unique immunosurveillance contributions are analyzed here in different clinical and experimental settings .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"It is beyond any doubt that the fast ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"potent , cytotoxic as well as non-cytolytic antiviral activities of cd T cells are critical in protecting the host against diverse viral pathogens .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}]}"}]}
{"paper_id": "62cd5be77a70a55d18199836987e521d4b992cbd", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRestoration of antigen-specific T cell immunity has the potential to clear persistent viral infection . T cell receptor ( TCR ) gene therapy can reconstitute CD8 T cell immunity in chronic patients . We cloned 10 virus-specific TCRs targeting 5 different viruses , causing chronic and acute infection . All 10 TCR genetic constructs were optimized for expression using a P2A sequence , codon optimization and the addition of a non-native disulfide bond . However , maximum TCR expression was only achieved after establishing the optimal orientation of the alpha and beta chains in the expression cassette ; 9/10 TCRs favored the beta-P2A-alpha orientation over alpha-P2A-beta . Optimal TCR expression was associated with a significant increase in the frequency of IFN-gamma1 T cells . In addition , activating cells for transduction in the presence of Toll-like receptor ligands further enhanced IFN-gamma production . Thus , we have built a virus-specific TCR library that has potential for therapeutic intervention in chronic viral infection or virus-related cancers .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Restoration of antigen-specific T cell immunity has the potential to clear persistent viral infection .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"T cell receptor ( TCR ) gene therapy can reconstitute CD8 T cell immunity in chronic patients .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"We cloned 10 virus-specific TCRs targeting 5 different viruses ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"causing chronic and acute infection .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"All 10 TCR genetic constructs were optimized for expression using a P2A sequence ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"codon optimization and the addition of a non-native disulfide bond .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"However , maximum TCR expression was only achieved after establishing the optimal orientation of the alpha and beta chains in the expression cassette ; 9/10 TCRs favored the beta-P2A-alpha orientation over alpha-P2A-beta .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Optimal TCR expression was associated with a significant increase in the frequency of IFN-gamma1 T cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"In addition , activating cells for transduction in the presence of Toll-like receptor ligands further enhanced IFN-gamma production .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Thus , we have built a virus-specific TCR library that has potential for therapeutic intervention in chronic viral infection or virus-related cancers .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "04bdb14ee4fde3edae739ffd6b0fc196aee7333e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCOVID-19 emerges as a pandemic disease with high mortality . Development of effective prevention and treatment is an urgent need . We reviewed TH17 responses in patients with SARS-CoV-2 and proposed an FDA approved JAK2 inhibitor Fedratinib for reducing mortality of patients with TH17 type immune profiles .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"COVID-19 emerges as a pandemic disease with high mortality .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Development of effective prevention and treatment is an urgent need .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"We reviewed TH17 responses in patients with SARS-CoV-2 and proposed an FDA approved JAK2 inhibitor Fedratinib for reducing mortality of patients with TH17 type immune profiles .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}]}"}]}
{"paper_id": "64fe1b9afa90e2e1ea0c1c10e2ae5ada566e270a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nA one year active surveillance program for influenza A viruses among avian species in a live-bird market ( LBM ) in Bangkok , Thailand was conducted in 2009 . Out of 970 samples collected , influenza A virus subtypes H4N6 ( n = 2 ) and H4N9 ( n = 1 ) were isolated from healthy Muscovy ducks . All three viruses were characterized by whole genome sequencing with subsequent phylogenetic analysis and genetic comparison . Phylogenetic analysis of all eight viral genes showed that the viruses clustered in the Eurasian lineage of influenza A viruses . Genetic analysis showed that H4N6 and H4N9 viruses display low pathogenic avian influenza characteristics . The HA cleavage site and receptor binding sites were conserved and resembled to LPAI viruses . This study is the first to report isolation of H4N6 and H4N9 viruses from birds in LBM in Thailand and shows the genetic diversity of the viruses circulating in the LBM . In addition , co-infection of H4N6 and H4N9 in the same Muscovy duck was observed .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"A one year active surveillance program for influenza A viruses among avian species in a live-bird market ( LBM ) in Bangkok ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Thailand was conducted in 2009 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Out of 970 samples collected ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"influenza A virus subtypes H4N6 ( n = 2 ) and H4N9 ( n = 1 ) were isolated from healthy Muscovy ducks .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"All three viruses were characterized by whole genome sequencing with subsequent phylogenetic analysis and genetic comparison .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Phylogenetic analysis of all eight viral genes showed that the viruses clustered in the Eurasian lineage of influenza A viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Genetic analysis showed that H4N6 and H4N9 viruses display low pathogenic avian influenza characteristics .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"The HA cleavage site and receptor binding sites were conserved and resembled to LPAI viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"This study is the first to report isolation of H4N6 and H4N9 viruses from birds in LBM in Thailand and shows the genetic diversity of the viruses circulating in the LBM .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"In addition , co-infection of H4N6 and H4N9 in the same Muscovy duck was observed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "25cd041ddd48e5ed81dea05a1fc841b1e4468d9e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nViral disease caused by the Yellow head virus ( YHV ) had great impact on economic loss in the aquaculture industry . Prevention or curing YHV disease is still not possible due to the lack of understanding of the basic mechanisms of YHV infection . In this report , the endocytosis inhibitors ( chlorpromazine ( CPZ ) , amiloride and methyl-β-cyclodextrin ( MβCD ) ) were used to identify the cellular entry pathway of YHV . Pretreating shrimp with CPZ but not amiloride or MβCD followed by YHV challenge resulted in a significant reduction of YHV levels , suggesting that YHV entered the shrimp cells via clathrin-mediated endocytosis . Next , the major component of the clathrin-coated vesicle , Penaeus monodon clathrin heavy chain ( PmCHC ) was cloned and characterized . The complete coding sequence of PmCHC is 5055 bp encoding a putative protein of 1684 amino acids . Specific silencing of PmCHC mRNA by dsRNA-PmCHC showed an inhibition of YHV replication for 48 h post YHV injection as well as exhibiting a delay in shrimp mortality . These results indicated that PmCHC was an essential component for YHV infection of shrimp cells .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Viral disease caused by the Yellow head virus ( YHV ) had great impact on economic loss in the aquaculture industry .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Prevention or curing YHV disease is still not possible due to the lack of understanding of the basic mechanisms of YHV infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"In this report , the endocytosis inhibitors ( chlorpromazine ( CPZ ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"amiloride and methyl-β-cyclodextrin ( MβCD ) ) were used to identify the cellular entry pathway of YHV .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Pretreating shrimp with CPZ but not amiloride or MβCD followed by YHV challenge resulted in a significant reduction of YHV levels ,\", \"label\": \"method\", \"decision_reference\": \"boundary method_vs_finding\", \"id\": 5}, {\"segment_text\": \"suggesting that YHV entered the shrimp cells via clathrin-mediated endocytosis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Next , the major component of the clathrin-coated vesicle ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Penaeus monodon clathrin heavy chain ( PmCHC ) was cloned and characterized .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"The complete coding sequence of PmCHC is 5055 bp encoding a putative protein of 1684 amino acids .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Specific silencing of PmCHC mRNA by dsRNA-PmCHC showed an inhibition of YHV replication for 48 h post YHV injection as well as exhibiting a delay in shrimp mortality .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"These results indicated that PmCHC was an essential component for YHV infection of shrimp cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}]}"}]}
{"paper_id": "a7fd820f0a5983f4254f8b6e0e03478bb7da244b", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMultiple sclerosis ( MS ) is an autoimmune disease in which autoreactive T cells specific to central nervous system ( CNS ) myelin antigens are activated . Although disease etiology remains unknown , coronaviruses are suspected to be involved in MS pathology . Molecular mimicry , the recognition of two antigens by a single immune cell , could be the mechanism explaining the link between a viral infection and MS through activation of myelin-reactive T cells by a virus infection in a genetically predisposed individual . Evidence supporting this hypothesis in humans has been accumulated in our laboratory . Human coronavirus ( HCoV ) - myelin cross-reactive T-cell lines ( TCL ) were predominantly found in MS patients compared to patients with other neurological or inflammatory diseases , or healthy controls . Moreover , virusmyelin T cell cross-reactivity was confirmed at the clonal level . Molecular mimicry between infectious pathogens such as the ubiquitous human respiratory coronaviruses could , in genetically susceptible individuals , play a role leading to the development of MS. Together with other possible mechanisms such as bystander effects , epitope spreading or even superantigenic activities , this pathogen-associated immune induction could play a role in maintaining and broadening the autoimmune response associated with MS pathology . autoimmunity , T cells , central nervous system , virus , molecular mimicry 1 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Multiple sclerosis ( MS ) is an autoimmune disease in which autoreactive T cells specific to central nervous system ( CNS ) myelin antigens are activated .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Although disease etiology remains unknown ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"coronaviruses are suspected to be involved in MS pathology .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Molecular mimicry , the recognition of two antigens by a single immune cell ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"could be the mechanism explaining the link between a viral infection and MS through activation of myelin-reactive T cells by a virus infection in a genetically predisposed individual .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Evidence supporting this hypothesis in humans has been accumulated in our laboratory .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Human coronavirus ( HCoV ) - myelin cross-reactive T-cell lines ( TCL ) were predominantly found in MS patients compared to patients with other neurological or inflammatory diseases , or healthy controls .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Moreover , virusmyelin T cell cross-reactivity was confirmed at the clonal level .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Molecular mimicry between infectious pathogens such as the ubiquitous human respiratory coronaviruses could ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"in genetically susceptible individuals , play a role leading to the development of MS. Together with other possible mechanisms such as bystander effects ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"epitope spreading or even superantigenic activities ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"this pathogen-associated immune induction could play a role in maintaining and broadening the autoimmune response associated with MS pathology .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"autoimmunity , T cells , central nervous system ,\", \"label\": \"finding\", \"decision_reference\": \"other.rule\", \"id\": 13}, {\"segment_text\": \"virus , molecular mimicry 1 .\", \"label\": \"finding\", \"decision_reference\": \"other.rule\", \"id\": 14}]}"}]}
{"paper_id": "04e8b80ed7a2ffd701f7fa9079698fe01c94f278", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRespiratory droplet characteristics are key to determine the droplet-bornepathogen transmission , which provide scientific basis for formulating the disease prevention from droplet transmission and control measures . Through studying the data information from existing documents , this paper gives the respiratory droplet characteristics , like size , concentration , velocity , etc. . Meanwhile , droplet evaporation,droplet-bornepathogen activity and their transmission are discussed . The droplet size is no significant difference with human health level , gender and age . The size of droplets produced by health people is between 0.1 and 10μm , it produced by patientsis between 0.05 and 10μm , and the patients ' dropletconcentration is higher . The coughed droplet concentrations change with the size into a peak rule . The velocity of the cough droplets is the biggest , the range of 10 to 25m/s , the transmission distance is more than 2m .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Respiratory droplet characteristics are key to determine the droplet-bornepathogen transmission ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"which provide scientific basis for formulating the disease prevention from droplet transmission and control measures .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Through studying the data information from existing documents ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"this paper gives the respiratory droplet characteristics ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"like size , concentration , velocity , etc. .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Meanwhile , droplet evaporation,droplet-bornepathogen activity and their transmission are discussed .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"The droplet size is no significant difference with human health level , gender and age .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"The size of droplets produced by health people is between 0.1 and 10μm ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"it produced by patientsis between 0.05 and 10μm ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"and the patients ' dropletconcentration is higher .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The coughed droplet concentrations change with the size into a peak rule .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"The velocity of the cough droplets is the biggest ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"the range of 10 to 25m/s ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"the transmission distance is more than 2m .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "bdca6cb34a68176f77ae340ef673557a3ad9bc08", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\npublicly funded repositories , such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source . These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active . 93 2.1.1 Genomic DNA and cDNA cloning If the foreign DNA is of bacterial origin , preparation of the insert fragment is relatively simple . Total bacterial DNA is purified , cleaved with a restriction endonuclease and Engineered Micro-organisms ( eds Temperature , pH , and cations affect the ability of Escherichia coli to mobilize plasmids in L broth and synthetic wastewater .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"publicly funded repositories , such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"93 2.1.1 Genomic DNA and cDNA cloning\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"If the foreign DNA is of bacterial origin ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"preparation of the insert fragment is relatively simple .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Total bacterial DNA is purified ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"cleaved with a restriction endonuclease and\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"Engineered Micro-organisms ( eds Temperature , pH , and cations affect the ability of Escherichia coli to mobilize plasmids in L broth and synthetic wastewater .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}]}"}]}
{"paper_id": "86161746859c22d29da637d687deda287607c69d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nDNA microarrays represent a powerful technology that enables whole-scale comparison of bacterial genomes . This , coupled with new methods to model DNA microarray data , is facilitating the development of robust comparative phylogenomics analyses . Such studies have dramatically increased our ability to differentiate between bacteria , highlighting previously undetected genetic differences and population structures and providing new insight into virulence and evolution of bacterial pathogens . Recent results from such studies have generated insights into the evolution of bacterial pathogens , the levels of diversity and plasticity in the genome of a species , as well as the differences in virulence amongst pathogenic bacteria . Comparative phylogenomics of pathogenic bacteria by microarray analysis Dorrell , Hinchliffe and Wren 621 Figure 1 Principles of comparative phylogenomics using DNA microarrays . For further details , see main body of text . www.sciencedirect.com Current Opinion in Microbiology 2005 , 8:620-626 Comparative phylogenomics of pathogenic bacteria by microarray analysis Dorrell , Hinchliffe and Wren 625 www.sciencedirect.com Current Opinion in Microbiology 2005 , 8:620-626\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"DNA microarrays represent a powerful technology that enables whole-scale comparison of bacterial genomes .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"This , coupled with new methods to model DNA microarray data ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"is facilitating the development of robust comparative phylogenomics analyses .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Such studies have dramatically increased our ability to differentiate between bacteria ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"highlighting previously undetected genetic differences and population structures and providing new insight into virulence and evolution of bacterial pathogens .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Recent results from such studies have generated insights into the evolution of bacterial pathogens ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"the levels of diversity and plasticity in the genome of a species ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"as well as the differences in virulence amongst pathogenic bacteria .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"Comparative phylogenomics of pathogenic bacteria by microarray analysis Dorrell ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"Hinchliffe and Wren 621 Figure 1 Principles of comparative phylogenomics using DNA microarrays .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"For further details , see main body of text .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 11}, {\"segment_text\": \"www.sciencedirect.com Current Opinion in Microbiology 2005 ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 12}, {\"segment_text\": \"8:620-626 Comparative phylogenomics of pathogenic bacteria by microarray analysis Dorrell ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 13}, {\"segment_text\": \"Hinchliffe and Wren 625 www.sciencedirect.com Current Opinion in Microbiology 2005 , 8:620-626\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 14}]}"}]}
{"paper_id": "364f3e45183f362e8398724c29d3b010436ce375", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAcute respiratory distress syndrome ( ARDS ) is common among mechanically ventilated children and accompanies up to 30 % of all pediatric intensive care unit deaths . Though ARDS diagnosis is based on clinical criteria , biological markers of acute lung damage have been extensively studied in adults and children . Biomarkers of inflammation , alveolar epithelial and capillary endothelial disruption , disordered coagulation , and associated derangements measured in the circulation and other body fluids , such as bronchoalveolar lavage , have improved our understanding of pathobiology of ARDS . The biochemical signature of ARDS has been increasingly well described in adult populations , and this has led to the identification of molecular phenotypes to augment clinical classifications . However , there is a paucity of data from pediatric ARDS ( pARDS ) patients . Biomarkers and molecular phenotypes have the potential to identify patients at high risk of poor outcomes , and perhaps inform the development of targeted therapies for specific groups of patients . Additionally , because of the lower incidence of and mortality from ARDS in pediatric patients relative to adults and lack of robust clinical predictors of outcome , there is an ongoing interest in biological markers as surrogate outcome measures . The recent definition of pARDS provides additional impetus for the measurement of established and novel biomarkers in future pediatric studies in order to further characterize this disease process . This chapter will review the currently available literature and discuss potential future directions for investigation into biomarkers in ARDS among children .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Acute respiratory distress syndrome ( ARDS ) is common among mechanically ventilated children and accompanies up to 30 % of all pediatric intensive care unit deaths .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Though ARDS diagnosis is based on clinical criteria ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"biological markers of acute lung damage have been extensively studied in adults and children .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Biomarkers of inflammation , alveolar epithelial and capillary endothelial disruption ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"disordered coagulation , and associated derangements measured in the circulation and other body fluids ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"such as bronchoalveolar lavage , have improved our understanding of pathobiology of ARDS .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"The biochemical signature of ARDS has been increasingly well described in adult populations ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"and this has led to the identification of molecular phenotypes to augment clinical classifications .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"However , there is a paucity of data from pediatric ARDS ( pARDS ) patients .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"Biomarkers and molecular phenotypes have the potential to identify patients at high risk of poor outcomes ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"and perhaps inform the development of targeted therapies for specific groups of patients .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"Additionally , because of the lower incidence of and mortality from ARDS in pediatric patients relative to adults and lack of robust clinical predictors of outcome ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"there is an ongoing interest in biological markers as surrogate outcome measures .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 13}, {\"segment_text\": \"The recent definition of pARDS provides additional impetus for the measurement of established and novel biomarkers in future pediatric studies in order to further characterize this disease process .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 14}, {\"segment_text\": \"This chapter will review the currently available literature and discuss potential future directions for investigation into biomarkers in ARDS among children .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}]}"}]}
{"paper_id": "68573eedbded1ad21d12a521f95676711c0feeae", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nObjective : Salmonella enterica remains a major cause of food-borne disease in humans , and Salmonella Typhimurium ( ST ) contamination of poultry products is a worldwide problem . Since macrophages play an essential role in controlling Salmonella infection , the aim of this study was to evaluate the effect of glycyrrhizic acid ( GA ) on immune function of chicken HD11 macrophages . Methods : Chicken HD11 macrophages were treated with GA ( 0 , 12.5 , 25 , 50 , 100 , 200 , 400 , or 800 μg/ml ) and lipopolysaccharide ( LPS , 500 ng/ml ) for 3 , 6 , 12 , 24 , or 48 h. Evaluated responses included phagocytosis , bacteria-killing , gene expression of cell surface molecules ( cluster of differentiation 40 ( CD40 ) , CD80 , CD83 , and CD197 ) and antimicrobial effectors ( inducible nitric oxide synthase ( iNOS ) , NADPH oxidase-1 ( NOX-1 ) , interferon-γ ( IFN-γ ) , LPS-induced tumor necrosis factor ( TNF ) - α factor ( LITAF ) , interleukin-6 ( IL-6 ) , and IL-10 ) , and production of nitric oxide ( NO ) and hydrogen peroxide ( H 2 O 2 ) . Results : GA increased the internalization of both fluorescein isothiocyanate ( FITC ) - dextran and ST by HD11 cells and markedly decreased the intracellular survival of ST. We found that the messenger RNA ( mRNA ) expression of cell surface molecules ( CD40 , CD80 , CD83 , and CD197 ) and cytokines ( IFN-γ , IL-6 , and IL-10 ) of HD11 cells was up-regulated following GA exposure . The expression of iNOS and NOX-1 was induced by GA and thereby the productions of NO and H 2 O 2 in HD11 cells were enhanced . Notably , it was verified that nuclear factor-κB ( NF-κB ) and c-Jun N-terminal kinase ( JNK ) pathways were responsible for GA-induced synthesis of NO and IFN-γ gene expression . Conclusions : Taken together , these results suggested that GA exhibits a potent immune regulatory effect to activate chicken macrophages and enhances Salmonella-killing capacity .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Objective : Salmonella enterica remains a major cause of food-borne disease in humans ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"and Salmonella Typhimurium ( ST ) contamination of poultry products is a worldwide problem .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Since macrophages play an essential role in controlling Salmonella infection ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"the aim of this study was to evaluate the effect of glycyrrhizic acid ( GA ) on immune function of chicken HD11 macrophages .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Methods : Chicken HD11 macrophages were treated with GA ( 0 , 12.5 , 25 , 50 , 100 , 200 , 400 , or 800 μg/ml ) and lipopolysaccharide ( LPS , 500 ng/ml ) for 3 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"6 , 12 , 24 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"or 48 h. Evaluated responses included phagocytosis ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"bacteria-killing , gene expression of cell surface molecules ( cluster of differentiation 40 ( CD40 ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"CD80 , CD83 , and CD197 ) and antimicrobial effectors ( inducible nitric oxide synthase ( iNOS ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"NADPH oxidase-1 ( NOX-1 ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"interferon-γ ( IFN-γ ) , LPS-induced tumor necrosis factor ( TNF ) - α factor ( LITAF ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"interleukin-6 ( IL-6 ) , and IL-10 ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"and production of nitric oxide ( NO ) and hydrogen peroxide ( H 2 O 2 ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"Results : GA increased the internalization of both fluorescein isothiocyanate ( FITC ) - dextran and ST by HD11 cells and markedly decreased the intracellular survival of ST. We found that the messenger RNA ( mRNA ) expression of cell surface molecules ( CD40 , CD80 , CD83 , and CD197 ) and cytokines ( IFN-γ , IL-6 , and IL-10 ) of HD11 cells was up-regulated following GA exposure .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"The expression of iNOS and NOX-1 was induced by GA and thereby the productions of NO and H 2 O 2 in HD11 cells were enhanced .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Notably , it was verified that nuclear factor-κB ( NF-κB ) and c-Jun N-terminal kinase ( JNK ) pathways were responsible for GA-induced synthesis of NO and IFN-γ gene expression .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Conclusions : Taken together , these results suggested that GA exhibits a potent immune regulatory effect to activate chicken macrophages and enhances Salmonella-killing capacity .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "e929f901fbdd9d3aab8e8c5da76e40985d9cb1d2", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe present study describes the development of SYBR Green based real-time polymerase chain reaction ( real-time PCR ) for detection and quantitation of canine parvovirus type 2 ( CPV 2 ) in faecal samples of dogs . In this assay , the primers were designed and custom-synthesized based on nucleotide sequence of VP2 gene of CPV 2 . A standard curve was plotted using 10-fold serial dilution of standard plasmid DNA and Ct value . The standard curve was found to be linear over a 10 − 7 dilution . The real-time PCR results were expressed as the number of DNA copies of CPV 2 per mg of faecal samples and showed range of 1.0 × 10 3 to 7.0 × 10 9 copies of viral DNA per mg of stool samples . The analytical sensitivity of the SYBR Green based real-time PCR was shown to be equivalent to 10 copies . Faecal samples ( 47 ) from dogs suspected of CPV 2 infection were analyzed by real-time PCR , haemagglutination ( HA ) assay and by a conventional PCR and 24 , 20 and 22 samples were found positive for CPV 2 , respectively . Comparison between the results of three different assays revealed that real-time PCR is more sensitive than HA and conventional PCR and allow the detection of low titers of CPV 2 in infected dogs .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The present study describes the development of SYBR Green based real-time polymerase chain reaction ( real-time PCR ) for detection and quantitation of canine parvovirus type 2 ( CPV 2 ) in faecal samples of dogs .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"In this assay , the primers were designed and custom-synthesized based on nucleotide sequence of VP2 gene of CPV 2 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"A standard curve was plotted using 10-fold serial dilution of standard plasmid DNA and Ct value .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"The standard curve was found to be linear over a 10 − 7 dilution .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"The real-time PCR results were expressed as the number of DNA copies of CPV 2 per mg of faecal samples and showed range of 1.0 × 10 3 to 7.0 × 10 9 copies of viral DNA per mg of stool samples .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"The analytical sensitivity of the SYBR Green based real-time PCR was shown to be equivalent to 10 copies .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Faecal samples ( 47 ) from dogs suspected of CPV 2 infection were analyzed by real-time PCR ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"haemagglutination ( HA ) assay and by a conventional PCR and 24 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"20 and 22 samples were found positive for CPV 2 , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Comparison between the results of three different assays revealed that real-time PCR is more sensitive than HA and conventional PCR and allow the detection of low titers of CPV 2 in infected dogs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "1e54b4c6d2a9fb30b0fa2e295d7d16fc521ead5c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nTo this insightful phrase , numerous biologists studying biodiversity have added the corollary : Everything in biology makes more sense in light of phylogeny . As portions of the Tree of Life ( e.g. , vertebrates , butterflies ) have been better resolved , together with the recent publication of the first rough draft tree of all named life ( see Chapter 3 ) , the scientific community , as well as the general public , have increasingly come to appreciate its value . Through yielding powerful insights into the past , the Tree of Life provides a means to interpret the patterns and processes of evolution , as well as the ability to predict the responses of life in the face of rapid environmental change . Broad knowledge of species relationships is fundamental , providing crucial new information regarding the discovery of medicines , combatting diseases , and crop improvement . This information has also had major impacts in the diverse fields of genomics , evolution , and development , while providing insights into the study of adaptation , speciation , community assembly , and ecosystem functioning . Given the many benefits , it is therefore hard to summarize , in a few words , the immense implications and applications of the Tree of Life to biology and human well-being . All of these benefits of a better knowledge of phylogeny and the Tree of Life are made possible for the same reason that a clear understanding of your own family tree is important-knowledge of relationships matters . We all seem to have a fascination with family trees-who were my ancestors ? How am I related to others ? In addition , we all understand clearly that if a close relative has a disease that is inherited , say a certain cancer , then there is a good probability that we may have inherited the genes for that trait ( Fig. 5.1 ) . In much the same way as understanding your family tree is enlightening , the Tree of Life similarly has informative and predictive value . We The Great Tree of Life\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"To this insightful phrase , numerous biologists studying biodiversity have added the corollary :\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Everything in biology makes more sense in light of phylogeny .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"As portions of the Tree of Life ( e.g. , vertebrates , butterflies ) have been better resolved ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"together with the recent publication of the first rough draft tree of all named life ( see Chapter 3 ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"the scientific community , as well as the general public ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"have increasingly come to appreciate its value .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Through yielding powerful insights into the past ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"the Tree of Life provides a means to interpret the patterns and processes of evolution ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"as well as the ability to predict the responses of life in the face of rapid environmental change .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"Broad knowledge of species relationships is fundamental ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"providing crucial new information regarding the discovery of medicines ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"combatting diseases , and crop improvement .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"This information has also had major impacts in the diverse fields of genomics ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}, {\"segment_text\": \"evolution , and development , while providing insights into the study of adaptation ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 14}, {\"segment_text\": \"speciation , community assembly , and ecosystem functioning .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 15}, {\"segment_text\": \"Given the many benefits , it is therefore hard to summarize ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 16}, {\"segment_text\": \"in a few words , the immense implications and applications of the Tree of Life to biology and human well-being .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 17}, {\"segment_text\": \"All of these benefits of a better knowledge of phylogeny and the Tree of Life are made possible for the same reason that a clear understanding of your own family tree is important-knowledge of relationships matters .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 18}, {\"segment_text\": \"We all seem to have a fascination with family trees-who were my ancestors ?\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 19}, {\"segment_text\": \"How am I related to others ?\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 20}, {\"segment_text\": \"In addition , we all understand clearly that if a close relative has a disease that is inherited ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 21}, {\"segment_text\": \"say a certain cancer , then there is a good probability that we may have inherited the genes for that trait ( Fig. 5.1 ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 22}, {\"segment_text\": \"In much the same way as understanding your family tree is enlightening ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 23}, {\"segment_text\": \"the Tree of Life similarly has informative and predictive value .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 24}, {\"segment_text\": \"We\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 25}, {\"segment_text\": \"The Great Tree of Life\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 26}]}"}]}
{"paper_id": "f20a4ca033637fcd68195ffdb405bcd7ff5c4ba3", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nHighlights d Structure of bnAb S9-3-37 bound to influenza hemagglutinin stem was determined d D3-9-encoded region of S9-3-37 contributes majority of the interaction surface with HA d D3-9 gene segment of S9-3-37 can engage the HA stem in two different reading frames d D3-9 gene segment represents a recurring mechanism for antibody targeting of HA stem SUMMARY Discovery and characterization of broadly neutralizing antibodies ( bnAbs ) to the influenza hemagglutinin ( HA ) stem have provided insights for the development of a universal flu vaccine . Identification of signature features common to bnAbs from different individuals will be key to guiding immunogen design . S9-3-37 is a bnAb isolated from a healthy H5N1 vaccinee . Here , structural characterization reveals that the D3-9 gene segment of S9-3-37 contributes most of the interaction surface with the highly conserved stem epitope on HA . Comparison with other influenza bnAb crystal structures indicates that the D3-9 segment provides a general mechanism for targeting HA stem . Interestingly , such bnAbs can approach the HA stem with vastly different angles and orientations . Moreover , D3-9 can be translated in different reading frames in different bnAbs yet still target the same HA stem pocket . Thus , the D3-9 gene segment in the human immune repertoire can provide a robust defense against influenza virus .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Highlights d Structure of bnAb S9-3-37 bound to influenza hemagglutinin stem was determined d D3-9-encoded region of S9-3-37 contributes majority of the interaction surface with HA d D3-9 gene segment of S9-3-37 can engage the HA stem in two different reading frames d D3-9 gene segment represents a recurring mechanism for antibody targeting of HA stem SUMMARY Discovery and characterization of broadly neutralizing antibodies ( bnAbs ) to the influenza hemagglutinin ( HA ) stem have provided insights for the development of a universal flu vaccine .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Identification of signature features common to bnAbs from different individuals will be key to guiding immunogen design .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"S9-3-37 is a bnAb isolated from a healthy H5N1 vaccinee .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Here , structural characterization reveals that the D3-9 gene segment of S9-3-37 contributes most of the interaction surface with the highly conserved stem epitope on HA .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Comparison with other influenza bnAb crystal structures indicates that the D3-9 segment provides a general mechanism for targeting HA stem .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Interestingly , such bnAbs can approach the HA stem with vastly different angles and orientations .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Moreover , D3-9 can be translated in different reading frames in different bnAbs yet still target the same HA stem pocket .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Thus , the D3-9 gene segment in the human immune repertoire can provide a robust defense against influenza virus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}]}"}]}
{"paper_id": "411b0ac3d72573bf6b15259802359f0a8c456a03", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe concept of matrix-assisted laser desorption/ionization mass spectrometry ( MALDI MS ) was first reported in 1985 . Since then , MALDI MS technologies have been evolving , and successfully used in genome , proteome , metabolome , and clinical diagnostic research . These technologies are highthroughput and sensitive . Emerging evidence has shown that they are not only useful in qualitative and quantitative analyses of proteins , but also of other types of biomolecules , such as DNA , glycans , and metabolites . Recently , parallel fragmentation monitoring ( PFM ) , which is a method comparable to selected reaction monitoring , has been reported . This highlights the potentials of MALDI-TOF / TOF tandem MS in quantification of metabolites . Here we critically review the applications of the major MALDI MS technologies , including MALDI-TOF MS , MALDI-TOF/TOF MS , SALDI-TOF MS , MALDI-QqQ MS , and SELDI-TOF MS , to the discovery and quantification of disease biomarkers in biological specimens , especially those in plasma/serum specimens . Using SELDI-TOF MS as an example , the presence of systemic bias in biomarker discovery studies employing MALDI-TOF MS and its possible solutions are also discussed in this chapter . The concepts of MALDI , SALDI , SELDI , and PFM are complementary to each other . Theoretically , all these technologies can be combined , leading to the next generation of the MALDI MS technologies . Real applications of MALDI MS technologies in clinical diagnostics should be forthcoming .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The concept of matrix-assisted laser desorption/ionization mass spectrometry ( MALDI MS ) was first reported in 1985 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Since then , MALDI MS technologies have been evolving ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"and successfully used in genome ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"proteome , metabolome , and clinical diagnostic research .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"These technologies are highthroughput and sensitive .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Emerging evidence has shown that they are not only useful in qualitative and quantitative analyses of proteins ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"but also of other types of biomolecules ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"such as DNA , glycans , and metabolites .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"Recently , parallel fragmentation monitoring ( PFM ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"which is a method comparable to selected reaction monitoring , has been reported .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"This highlights the potentials of MALDI-TOF / TOF tandem MS in quantification of metabolites .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"Here we critically review the applications of the major MALDI MS technologies ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}, {\"segment_text\": \"including MALDI-TOF MS , MALDI-TOF/TOF MS ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 13}, {\"segment_text\": \"SALDI-TOF MS , MALDI-QqQ MS ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 14}, {\"segment_text\": \"and SELDI-TOF MS , to the discovery and quantification of disease biomarkers in biological specimens ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 15}, {\"segment_text\": \"especially those in plasma/serum specimens .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 16}, {\"segment_text\": \"Using SELDI-TOF MS as an example ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 17}, {\"segment_text\": \"the presence of systemic bias in biomarker discovery studies employing MALDI-TOF MS and its possible solutions are also discussed in this chapter .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"The concepts of MALDI , SALDI ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"SELDI , and PFM are complementary to each other .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"Theoretically , all these technologies can be combined ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"leading to the next generation of the MALDI MS technologies .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"Real applications of MALDI MS technologies in clinical diagnostics should be forthcoming .\", \"label\": \"finding\", \"decision_reference\": \"\", \"id\": 23}]}"}]}
{"paper_id": "adbfd5297c83ec9c3bec89f2cf68b2715034c4d4", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe renin angiotensin system ( RAS ) consists of the systemic hormone system , critically involved in regulation and homeostasis of normal physiological functions ( i.e. blood pressure ( BP ) , blood volume regulation ) , and an independent brain RAS , which is involved in the regulation of many functions such as memory , central control of BP and metabolic functions . In general terms , the RAS consists of two opposing axes ; the ` classical axis ' mediated primarily by Angiotensin II ( Ang II ) , and the ` alternative axis ' mediated mainly by Angiotensin - ( 1-7 ) ( Ang - ( 1-7 ) ) . An imbalance of these two opposing axes is thought to exist between genders and is thought to contribute to the pathology of cardiovascular conditions such as hypertension , a stroke co-morbidity . Ischaemic stroke pathophysiology has been shown to be influenced by components of the RAS with specific RAS receptor antagonists and agonists improving outcome in experimental models of stroke . Manipulation of the two opposing axes following acute ischaemic stroke may provide an opportunity for protection of the neurovascular unit , particularly in the presence of pre-existing co-morbidities where the balance may be shifted . In the present review we will give an overview of the experimental stroke studies that have investigated pharmacological interventions of the RAS .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The renin angiotensin system ( RAS ) consists of the systemic hormone system ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"critically involved in regulation and homeostasis of normal physiological functions ( i.e. blood pressure ( BP ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"blood volume regulation ) , and an independent brain RAS ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"which is involved in the regulation of many functions such as memory ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"central control of BP and metabolic functions .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"In general terms , the RAS consists of two opposing axes ; the ` classical axis ' mediated primarily by Angiotensin II ( Ang II ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"and the ` alternative axis ' mediated mainly by Angiotensin - ( 1-7 ) ( Ang - ( 1-7 ) ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"An imbalance of these two opposing axes is thought to exist between genders and is thought to contribute to the pathology of cardiovascular conditions such as hypertension , a stroke co-morbidity .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"Ischaemic stroke pathophysiology has been shown to be influenced by components of the RAS with specific RAS receptor antagonists and agonists improving outcome in experimental models of stroke .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"Manipulation of the two opposing axes following acute ischaemic stroke may provide an opportunity for protection of the neurovascular unit ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"particularly in the presence of pre-existing co-morbidities where the balance may be shifted .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"In the present review we will give an overview of the experimental stroke studies that have investigated pharmacological interventions of the RAS .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}]}"}]}
{"paper_id": "8d3f0c18b7b274179244f57cd8f66e185a009dd5", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nInterleukin-11 ( IL-11 ) , a well-known anti-inflammatory factor , provides protection from intestinal epithelium damage caused by physical or chemical factors . However , little is known of the role of IL-11 during viral infections . In this study , IL-11 expression at mRNA and protein levels were found to be high in Vero cells and the jejunum of piglets during porcine epidemic diarrhea virus ( PEDV ) infection , while IL-11 expression was found to be positively correlated with the level of viral infection . Pretreatment with recombinant porcine IL-11 ( pIL-11 ) was found to suppress PEDV replication in Vero E6 cells , while IL-11 knockdown promoted viral infection . Furthermore , pIL-11 was found to inhibit viral infection by preventing PEDV-mediated apoptosis of cells by activating the IL-11 / STAT3 signaling pathway . Conversely , application of a STAT3 phosphorylation inhibitor significantly antagonized the anti-apoptosis function of pIL-11 and counteracted its inhibition of PEDV . Our data suggest that IL-11 is a newfound PEDV-inducible cytokine , and its production enhances the anti-apoptosis ability of epithelial cells against PEDV infection . The potential of IL-11 to be used as a novel therapeutic against devastating viral diarrhea in piglets deserves more attention and study .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Interleukin-11 ( IL-11 ) , a well-known anti-inflammatory factor ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"provides protection from intestinal epithelium damage caused by physical or chemical factors .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"However , little is known of the role of IL-11 during viral infections .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"In this study , IL-11 expression at mRNA and protein levels were found to be high in Vero cells and the jejunum of piglets during porcine epidemic diarrhea virus ( PEDV ) infection ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"while IL-11 expression was found to be positively correlated with the level of viral infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Pretreatment with recombinant porcine IL-11 ( pIL-11 ) was found to suppress PEDV replication in Vero E6 cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"while IL-11 knockdown promoted viral infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Furthermore , pIL-11 was found to inhibit viral infection by preventing PEDV-mediated apoptosis of cells by activating the IL-11 / STAT3 signaling pathway .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Conversely , application of a STAT3 phosphorylation inhibitor significantly antagonized the anti-apoptosis function of pIL-11 and counteracted its inhibition of PEDV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Our data suggest that IL-11 is a newfound PEDV-inducible cytokine ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"and its production enhances the anti-apoptosis ability of epithelial cells against PEDV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"The potential of IL-11 to be used as a novel therapeutic against devastating viral diarrhea in piglets deserves more attention and study .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}]}"}]}
{"paper_id": "6416d311b8e5e360921299299fc25f039aac823a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe etiological agent of severe acute respiratory syndrome ( SARS ) has been identified as a novel coronavirus SARS-CoV . Similar to other coronaviruses , spike ( S ) - glycoprotein of the virus interacts with a cellular receptor and mediates membrane fusion to allow viral entry into susceptible target cells . Accordingly , S-protein plays an important role in virus infection cycle and is the primary target of neutralizing antibodies . To begin to understand its biochemical and immunological properties , we expressed both full-length and ectodomain of the protein in various primate cells . Our results show that the protein has an electrophoretic mobility of about 160 -170 kDa . The protein is glycosylated with high mannose and/or hybrid oligosaccharides , which account for approximately 30 kDa of the apparent protein mass . The detection of S-protein by immunoassays was difficult using human convalescent sera , suggesting that the protein may not elicit strong humoral immune response in virus-infected patients . We were able to pseudotype murine leukemia virus particles with S-protein and produce SARS pseudoviruses . Pseudoviruses infected Vero E6 cells in a pH-independent manner and the infection could be specifically inhibited by convalescent sera . Consistent with low levels of antibodies against S-protein , neutralizing activity was weak with 50 % neutralization titers ranging between 1:15 to 1:25 . To facilitate quantifying pseudovirus-infected cells , which are stained blue with X-Gal , we devised an automated procedure using an ELISPOT analyzer . The high-throughput capacity of this procedure and the safety of using SARS pseudoviruses should make possible large-scale analyses of neutralizing antibody responses against SARS-CoV . D\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The etiological agent of severe acute respiratory syndrome ( SARS ) has been identified as a novel coronavirus SARS-CoV .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Similar to other coronaviruses , spike ( S ) - glycoprotein of the virus interacts with a cellular receptor and mediates membrane fusion to allow viral entry into susceptible target cells .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Accordingly , S-protein plays an important role in virus infection cycle and is the primary target of neutralizing antibodies .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"To begin to understand its biochemical and immunological properties ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"we expressed both full-length and ectodomain of the protein in various primate cells .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Our results show that the protein has an electrophoretic mobility of about 160 -170 kDa .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"The protein is glycosylated with high mannose and/or hybrid oligosaccharides ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"which account for approximately 30 kDa of the apparent protein mass .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"The detection of S-protein by immunoassays was difficult using human convalescent sera ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"suggesting that the protein may not elicit strong humoral immune response in virus-infected patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"We were able to pseudotype murine leukemia virus particles with S-protein and produce SARS pseudoviruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Pseudoviruses infected Vero E6 cells in a pH-independent manner and the infection could be specifically inhibited by convalescent sera .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Consistent with low levels of antibodies against S-protein ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"neutralizing activity was weak with 50 % neutralization titers ranging between 1:15 to 1:25 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"To facilitate quantifying pseudovirus-infected cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"which are stained blue with X-Gal ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"we devised an automated procedure using an ELISPOT analyzer .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"The high-throughput capacity of this procedure and the safety of using SARS pseudoviruses should make possible large-scale analyses of neutralizing antibody responses against SARS-CoV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"D\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 19}]}"}]}
{"paper_id": "4faa402afa2be08dbff4034ba0faf50944d4c76c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe complexities of the dynamic processes and their control associated with biological and ecological systems offer many challenges for the control engineer . Over the past decades the application of dynamic modelling and control has aided understanding of their complexities . At the same time using such complex systems as test-beds for new control methods has highlighted their limitations ( e.g. in relation to system identification ) and has thus acted as a catalyst for methodological advance . This paper continues the theme of exploring opportunities and achievements in applying modelling and control in the bio-and ecological domains .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The complexities of the dynamic processes and their control associated with biological and ecological systems offer many challenges for the control engineer .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Over the past decades the application of dynamic modelling and control has aided understanding of their complexities .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"At the same time using such complex systems as test-beds for new control methods has highlighted their limitations ( e.g. in relation to system identification ) and has thus acted as a catalyst for methodological advance .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"This paper continues the theme of exploring opportunities and achievements in applying modelling and control in the bio-and ecological domains .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}]}"}]}
{"paper_id": "7817b03a433df4b3f93127feac4b0d8090c5b56c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\na b s t r a c t a r t i c l e i n f o Purpose : COVID-19 ( coronavirus disease 2019 ) is a public health emergency of international concern . As of this time , there is no known effective pharmaceutical treatment , although it is much needed for patient contracting the severe form of the disease . The aim of this systematic review was to summarize the evidence regarding chloroquine for the treatment of COVID-19 . Methods : PubMed , EMBASE , and three trial Registries were searched for studies on the use of chloroquine in patients with COVID-19 . Results : We included six articles ( one narrative letter , one in-vitro study , one editorial , expert consensus paper , two national guideline documents ) and 23 ongoing clinical trials in China . Chloroquine seems to be effective in limiting the replication of SARS-CoV-2 ( virus causing COVID-19 ) in vitro . Conclusions : There is rationale , pre-clinical evidence of effectiveness and evidence of safety from long-time clinical use for other indications to justify clinical research on chloroquine in patients with COVID-19 . However , clinical use should either adhere to the Monitored Emergency Use of Unregistered Interventions ( MEURI ) framework or be ethically approved as a trial as stated by the World Health Organization . Safety data and data from high-quality clinical trials are urgently needed .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"a b s t r a c t a r t i c l e i n f o\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 1}, {\"segment_text\": \"Purpose : COVID-19 ( coronavirus disease 2019 ) is a public health emergency of international concern .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"As of this time , there is no known effective pharmaceutical treatment ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"although it is much needed for patient contracting the severe form of the disease .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"The aim of this systematic review was to summarize the evidence regarding chloroquine for the treatment of COVID-19 .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Methods : PubMed , EMBASE ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"and three trial Registries were searched for studies on the use of chloroquine in patients with COVID-19 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Results : We included six articles ( one narrative letter , one in-vitro study , one editorial , expert consensus paper , two national guideline documents ) and 23 ongoing clinical trials in China .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"Chloroquine seems to be effective in limiting the replication of SARS-CoV-2 ( virus causing COVID-19 ) in vitro .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"Conclusions : There is rationale ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"pre-clinical evidence of effectiveness and evidence of safety from long-time clinical use for other indications to justify clinical research on chloroquine in patients with COVID-19 .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"However , clinical use should either adhere to the Monitored Emergency Use of Unregistered Interventions ( MEURI ) framework or be ethically approved as a trial as stated by the World Health Organization .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"Safety data and data from high-quality clinical trials are urgently needed .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}]}"}]}
{"paper_id": "9104c8bed3340e783a7a0a820ff269711f39bc8f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nA 62-year-old man presented to our hospital for the further evaluation and treatment of his back pain , general fatigue , and dyspnea , which had developed 4 days after the 29th administration of nivolumab to treat his lung cancer . Based on his clinical history , elevated serum cardiac enzyme values , and cardiac magnetic resonance ( CMR ) imaging and myocardial biopsy findings , he was diagnosed with myocarditis induced by nivolumab . Corticosteroid therapy improved his condition , and CMR performed on hospital day 11 also showed remarkable improvement . Although nivolumab-induced myocarditis is rare , cardiologists should consider it when encountering patients treated with such a drug for malignant disease .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"A 62-year-old man presented to our hospital for the further evaluation and treatment of his back pain ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"general fatigue , and dyspnea ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"which had developed 4 days after the 29th administration of nivolumab to treat his lung cancer .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Based on his clinical history ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"elevated serum cardiac enzyme values ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"and cardiac magnetic resonance ( CMR ) imaging and myocardial biopsy findings ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"he was diagnosed with myocarditis induced by nivolumab .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"Corticosteroid therapy improved his condition ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and CMR performed on hospital day 11 also showed remarkable improvement .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Although nivolumab-induced myocarditis is rare ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"cardiologists should consider it when encountering patients treated with such a drug for malignant disease .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}]}"}]}
{"paper_id": "a43db4dbbe6272ff71bcd5dc9cbf29bad9cd958e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nTetraspanins are suggested to regulate the composition of cell membrane components and control intracellular transport , which leaves them vulnerable to utilization by pathogens such as human papillomaviruses ( HPV ) and cytomegaloviruses ( HCMV ) to facilitate host cell entry and subsequent infection . In this study , by means of cellular depletion , the cluster of differentiation ( CD ) tetraspanins CD9 , CD63 , and CD151 were found to reduce HPV16 infection in HeLa cells by 50 to 80 % . Moreover , we tested recombinant proteins or peptides of specific tetraspanin domains on their effect on the most oncogenic HPV type , HPV16 , and HCMV . We found that the C-terminal tails of CD63 and CD151 significantly inhibited infections of both HPV16 and HCMV . Although CD9 was newly identified as a key cellular factor for HPV16 infection , the recombinant CD9 C-terminal peptide had no effect on infection . Based on the determined half-maximal inhibitory concentration ( IC 50 ) , we classified CD63 and CD151 C-terminal peptides as moderate to potent inhibitors of HPV16 infection in HeLa and HaCaT cells , and in EA.hy926 , HFF ( human foreskin fibroblast ) cells , and HEC-LTT ( human endothelial cell-large T antigen and telomerase ) cells for HCMV , respectively . These results indicate that HPV16 and HCMV share similar cellular requirements for their entry into host cells and reveal the necessity of the cytoplasmic CD151 and CD63 C-termini in virus infections . Furthermore , this highlights the suitability of these peptides for functional investigation of tetraspanin domains and as inhibitors of pathogen infections .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Tetraspanins are suggested to regulate the composition of cell membrane components and control intracellular transport ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"which leaves them vulnerable to utilization by pathogens such as human papillomaviruses ( HPV ) and cytomegaloviruses ( HCMV ) to facilitate host cell entry and subsequent infection .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"In this study , by means of cellular depletion ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"the cluster of differentiation ( CD ) tetraspanins CD9 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"CD63 , and CD151 were found to reduce HPV16 infection in HeLa cells by 50 to 80 % .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Moreover , we tested recombinant proteins or peptides of specific tetraspanin domains on their effect on the most oncogenic HPV type , HPV16 , and HCMV .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"We found that the C-terminal tails of CD63 and CD151 significantly inhibited infections of both HPV16 and HCMV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Although CD9 was newly identified as a key cellular factor for HPV16 infection ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"the recombinant CD9 C-terminal peptide had no effect on infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Based on the determined half-maximal inhibitory concentration ( IC 50 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"we classified CD63 and CD151 C-terminal peptides as moderate to potent inhibitors of HPV16 infection in HeLa and HaCaT cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and in EA.hy926 , HFF ( human foreskin fibroblast ) cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"and HEC-LTT ( human endothelial cell-large T antigen and telomerase ) cells for HCMV , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"These results indicate that HPV16 and HCMV share similar cellular requirements for their entry into host cells and reveal the necessity of the cytoplasmic CD151 and CD63 C-termini in virus infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Furthermore , this highlights the suitability of these peptides for functional investigation of tetraspanin domains and as inhibitors of pathogen infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}]}"}]}
{"paper_id": "f383499514eace4a8aa09fe364d17db3861fedd2", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nNext-generation sequencing ( NGS ) . High-throughput , massively parallel sequencing technology that is used in various applications , including whole-genome sequencing , exome sequencing and RNA sequencing . Abstract | With the emergence of RNA sequencing ( RNA-seq ) technologies , RNA-based biomolecules hold expanded promise for their diagnostic , prognostic and therapeutic applicability in various diseases , including cancers and infectious diseases . Detection of gene fusions and differential expression of known disease-causing transcripts by RNA-seq represent some of the most immediate opportunities . However , it is the diversity of RNA species detected through RNA-seq that holds new promise for the multi-faceted clinical applicability of RNA-based measures , including the potential of extracellular RNAs as non-invasive diagnostic indicators of disease . Ongoing efforts towards the establishment of benchmark standards , assay optimization for clinical conditions and demonstration of assay reproducibility are required to expand the clinical utility of RNA-seq . © 2 0 1 6 M a c m i l l a n P u b l i s h e r s L i m i t e d . A l l r i g h t s r e s e r v e d . A technology platform that does not depend on genome annotation , or on predesigned species-specific or transcript-specific probes , for transcript measurement . RNA-seq technology functions as an open platform allowing for unbiased detection of both known and novel transcripts .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Next-generation sequencing ( NGS ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"High-throughput , massively parallel sequencing technology that is used in various applications ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"including whole-genome sequencing , exome sequencing and RNA sequencing .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Abstract | With the emergence of RNA sequencing ( RNA-seq ) technologies ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"RNA-based biomolecules hold expanded promise for their diagnostic ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"prognostic and therapeutic applicability in various diseases ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"including cancers and infectious diseases .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Detection of gene fusions and differential expression of known disease-causing transcripts by RNA-seq represent some of the most immediate opportunities .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"However , it is the diversity of RNA species detected through RNA-seq that holds new promise for the multi-faceted clinical applicability of RNA-based measures ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"including the potential of extracellular RNAs as non-invasive diagnostic indicators of disease .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"Ongoing efforts towards the establishment of benchmark standards ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"assay optimization for clinical conditions and demonstration of assay reproducibility are required to expand the clinical utility of RNA-seq .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"© 2 0 1 6 M a c m i l l a n P u b l i s h e r s L i m i t e d .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 13}, {\"segment_text\": \"A l l r i g h t s r e s e r v e d .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 14}, {\"segment_text\": \"A technology platform that does not depend on genome annotation ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 15}, {\"segment_text\": \"or on predesigned species-specific or transcript-specific probes , for transcript measurement .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 16}, {\"segment_text\": \"RNA-seq technology functions as an open platform allowing for unbiased detection of both known and novel transcripts .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 17}]}"}]}
{"paper_id": "730913e0ef72862f884eb8a2bade5ebd55688d95", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPurpose : This study was designed to identify factors associated with death by 6 months post-intensive care unit ( ICU ) discharge and to develop a practical mortality risk score for extracorporeal membrane oxygenation ( ECMO ) treated acute respiratory distress syndrome ( ARDS ) patients . We also assessed long-term survivors ' healthrelated quality of life ( HRQL ) , respiratory symptoms , and anxiety , depression and post-traumatic stress disorder ( PTSD ) frequencies . Methods : Data from 140 ECMO-treated ARDS patients admitted to three French ICUs ( 2008-2012 ) were analyzed . ICU survivors contacted ( 6 months post-ICU discharge were assessed for HRQL , psychological and PTSD status . Results : Main ARDS etiologies were bacterial ( 45 % ) , influenza A ( H 1 N 1 ) ( 26 % ) and post-operative ( 17 % ) pneumonias . Six months post-ICU discharge , 84 ( 60 % ) patients were still alive . Based on multivariable logistic regression analysis , the PRESERVE ( PRedicting dEath for SEvere ARDS on VV-ECMO ) score ( 0-14 points ) was constructed with eight pre-ECMO parameters , i.e. age , body mass index , immunocompromised status , prone positioning , days of mechanical ventilation , sepsis-related organ failure assessment , plateau pressure andpositive end-expiratory pressure . Six-month post-ECMO initiation cumulative probabilities of survival were 97 , 79 , 54 and 16 % for PRESERVE classes 0-2 , 3-4 , 5-6 and C7 ( p \\ 0.001 ) , respectively . HRQL evaluation in 80 % of the 6-month survivors revealed satisfactory mental health but persistent physical and emotional-related difficulties , with anxiety , depression or PTSD symptoms reported , by 34 , 25 or 16 % , respectively . Conclusions : The PRESERVE score might help ICU physicians select appropriate candidates for ECMO among severe ARDS patients . Future studies should also focus on physical and psychosocial rehabilitation that could lead to improved HRQL in this population .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Purpose : This study was designed to identify factors associated with death by 6 months post-intensive care unit ( ICU ) discharge and to develop a practical mortality risk score for extracorporeal membrane oxygenation ( ECMO ) treated acute respiratory distress syndrome ( ARDS ) patients .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"We also assessed long-term survivors ' healthrelated quality of life ( HRQL ) ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"respiratory symptoms , and anxiety ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"depression and post-traumatic stress disorder ( PTSD ) frequencies .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Methods : Data from 140 ECMO-treated ARDS patients admitted to three French ICUs ( 2008-2012 ) were analyzed .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"ICU survivors contacted ( 6 months post-ICU discharge were assessed for HRQL , psychological and PTSD status .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Results : Main ARDS etiologies were bacterial ( 45 % ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"influenza A ( H 1 N 1 ) ( 26 % ) and post-operative ( 17 % ) pneumonias .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Six months post-ICU discharge , 84 ( 60 % ) patients were still alive .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Based on multivariable logistic regression analysis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"the PRESERVE ( PRedicting dEath for SEvere ARDS on VV-ECMO ) score ( 0-14 points ) was constructed with eight pre-ECMO parameters ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"i.e. age , body mass index ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"immunocompromised status , prone positioning ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"days of mechanical ventilation , sepsis-related organ failure assessment ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"plateau pressure andpositive end-expiratory pressure .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Six-month post-ECMO initiation cumulative probabilities of survival were 97 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"79 , 54 and 16 % for PRESERVE classes 0-2 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"3-4 , 5-6 and C7 ( p \\\\ 0.001 ) , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"HRQL evaluation in 80 % of the 6-month survivors revealed satisfactory mental health but persistent physical and emotional-related difficulties ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"with anxiety , depression or PTSD symptoms reported ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"by 34 , 25 or 16 % , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"Conclusions : The PRESERVE score might help ICU physicians select appropriate candidates for ECMO among severe ARDS patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"Future studies should also focus on physical and psychosocial rehabilitation that could lead to improved HRQL in this population .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}]}"}]}
{"paper_id": "ae747f2be1a6a0370ad979fafa7783c6e57602cd", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nInfectious diseases that are caused by pathogenic microorganisms can spread fast and far , from one person to another , directly or indirectly . Prompt quarantining of the infected from the rest , coupled with contact tracing , has been an effective measure to encounter outbreaks . However , urban life and international travel make containment difficult . Furthermore , the length of incubation periods of some contagious diseases like SARS enable infected passengers to elude health screenings before first symptoms appear and thus to carry the disease further . Detecting and visualizing contact-tracing networks , and immediately identifying the routes of infection , are thus important . We apply information visualization and hidden cluster detection for finding cliques of potentially infected people during incubation . Preemptive control and early quarantine are hence possible by our method . Our prototype Infectious Disease Detection and Quarantine Management System ( IDDQMS ) , which can identify and trace clusters of infection by mining patients ' history , is introduced in this paper .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Infectious diseases that are caused by pathogenic microorganisms can spread fast and far ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"from one person to another , directly or indirectly .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Prompt quarantining of the infected from the rest ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"coupled with contact tracing , has been an effective measure to encounter outbreaks .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"However , urban life and international travel make containment difficult .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Furthermore , the length of incubation periods of some contagious diseases like SARS enable infected passengers to elude health screenings before first symptoms appear and thus to carry the disease further .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Detecting and visualizing contact-tracing networks ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"and immediately identifying the routes of infection , are thus important .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"We apply information visualization and hidden cluster detection for finding cliques of potentially infected people during incubation .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Preemptive control and early quarantine are hence possible by our method .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Our prototype Infectious Disease Detection and Quarantine Management System ( IDDQMS ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"which can identify and trace clusters of infection by mining patients ' history ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"is introduced in this paper .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "53a7b62173e65ffc66609a603cfde43cfa267e40", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nObjectives : The objective of this paper is to assess historical and recent health reform efforts in China . We provide a brief history of the Chinese healthcare system since 1949 as context for the current healthcare ; examine the factors that led to recent efforts to reestablish community-based care in China ; and identify the challenges associated with attaining a sustainable and quality community healthcare system . Methods : Based on literature review and publicly available data in China , the paper will present a historical case study analysis of health policy change of CHOs in China and provide policy evaluation , and the paper provided policy suggestions . Results : We find that the government 's recent efforts to emphasize the significance of community healthcare services in China have started to change patterns of healthcare use , but many problems still inhibit the development of CHOs , including unsustainable governmental roles , issues of human resource inadequacy and laggard GP practice , poorly designed payment schemes , patient 's trust crisis and continue to inhibit the development of community-based primary care . Conclusions : Additional policy efforts to help CHOs ' development are needed . Recent government investments in public health and primary care alone are not sufficient and could not be sustainable . It will not until long-term self-sustaining mechanisms to relieve an omnipotent government are established , including competent community doctors ( GP ) system , supportive social insurance reimbursement , appropriate financial incentives to providers , better transparency and accountability , as well as a more regulated referral system , a legitimate , sustainable and quality community health system could be attained .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Objectives : The objective of this paper is to assess historical and recent health reform efforts in China .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"We provide a brief history of the Chinese healthcare system since 1949 as context for the current healthcare ; examine the factors that led to recent efforts to reestablish community-based care in China ; and identify the challenges associated with attaining a sustainable and quality community healthcare system .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"Methods : Based on literature review and publicly available data in China ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"the paper will present a historical case study analysis of health policy change of CHOs in China and provide policy evaluation ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"and the paper provided policy suggestions .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Results : We find that the government 's recent efforts to emphasize the significance of community healthcare services in China have started to change patterns of healthcare use ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"but many problems still inhibit the development of CHOs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"including unsustainable governmental roles , issues of human resource inadequacy and laggard GP practice ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"poorly designed payment schemes , patient 's trust crisis and continue to inhibit the development of community-based primary care .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Conclusions : Additional policy efforts to help CHOs ' development are needed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Recent government investments in public health and primary care alone are not sufficient and could not be sustainable .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"It will not until long-term self-sustaining mechanisms to relieve an omnipotent government are established ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"including competent community doctors ( GP ) system ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"supportive social insurance reimbursement , appropriate financial incentives to providers ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"better transparency and accountability , as well as a more regulated referral system ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"a legitimate , sustainable and quality community health system could be attained .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "dde67bba5fe26a26718e2a09500f31e189d68a9f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nDrinking water is a major source of microbial pathogens in developing regions , although poor sanitation and food sources are integral to enteric pathogen exposure . Gastrointestinal disease outcomes are also more severe , due to under-nutrition and lack of intervention strategies in these regions . Poor water quality , sanitation and hygiene account for some 1.7 million deaths a year world-wide ( 3.1 % of all deaths and 3.7 % of all DALY 's ) , mainly through infectious diarrhoea . Nine out of 10 such deaths are in children and virtually all of the deaths are in developing countries . Major enteric pathogens in these children include : rotavirus , Campylobacter jejuni , enterotoxigenic Escherichia coli , Shigella spp. and Vibrio cholerae O1 , and possibly enteropathogenic E. coli , Aeromonas spp. . V. cholerae O139 , enterotoxigenic Bacteroides fragilis , Clostridium difficile and Cryptosporidium parvum . All except the latter are easily control by chlorination of water , but recontamination of treated water is a huge problem . Emerging environmental pathogens , such as Helicobacter pylori and Burkholderia pseudomallei , may well be of significance in some regions . In adults , much less is understood of various sequellae such as myocarditis , diabetes , reactive arthritis and cancers some months-years after initial infections . So in addition to the traditional pathogens ( helminths , Entamoeba histolytica , Giardia lamblia hepatitis A and E ) various enteroviruses , C. jejuni and H. pylori are emerging issues in adults .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Drinking water is a major source of microbial pathogens in developing regions ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"although poor sanitation and food sources are integral to enteric pathogen exposure .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Gastrointestinal disease outcomes are also more severe ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"due to under-nutrition and lack of intervention strategies in these regions .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Poor water quality , sanitation and hygiene account for some 1.7 million deaths a year world-wide ( 3.1 % of all deaths and 3.7 % of all DALY 's ) , mainly through infectious diarrhoea .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Nine out of 10 such deaths are in children and virtually all of the deaths are in developing countries .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"Major enteric pathogens in these children include : rotavirus ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"Campylobacter jejuni , enterotoxigenic Escherichia coli ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"Shigella spp. and Vibrio cholerae O1 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"and possibly enteropathogenic E. coli , Aeromonas spp. .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"V. cholerae O139 , enterotoxigenic Bacteroides fragilis ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"Clostridium difficile and Cryptosporidium parvum .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"All except the latter are easily control by chlorination of water ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 13}, {\"segment_text\": \"but recontamination of treated water is a huge problem .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 14}, {\"segment_text\": \"Emerging environmental pathogens , such as Helicobacter pylori and Burkholderia pseudomallei ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 15}, {\"segment_text\": \"may well be of significance in some regions .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 16}, {\"segment_text\": \"In adults , much less is understood of various sequellae such as myocarditis ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 17}, {\"segment_text\": \"diabetes , reactive arthritis and cancers some months-years after initial infections .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 18}, {\"segment_text\": \"So in addition to the traditional pathogens ( helminths , Entamoeba histolytica , Giardia lamblia hepatitis A and E ) various enteroviruses ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 19}, {\"segment_text\": \"C. jejuni and H. pylori are emerging issues in adults .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 20}]}"}]}
{"paper_id": "e0393328e9f59159671bff8a33e26edbdab28034", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSustained adaptive immunity to pathogens provides effective protection against infections , and effector cells located at the site of infection ensure rapid response to the challenge . Both are essential for the success of vaccine development . To explore new vaccination approach against Mycobacterium tuberculosis ( M.tb ) infection , we have shown that Rv3615c , identified as ESX-1 substrate protein C of M.tb but not expressed in BCG , induced a dominant Th1-type response of CD4 + T cells from patients with tuberculosis pleurisy , which suggests a potential candidate for vaccine development . But subcutaneous immunization with Rv3615c induced modest T-cell responses systemically , and showed suboptimal protection against virulent M.tb challenge at the site of infection . Here , we use a mouse model to demonstrate that intranasal immunization with Rv3615c induces sustained capability of adaptive CD4 + T-and B-cell responses in lung parenchyma and airway . Rv3615c contains a dominant epitope of mouse CD4 + T cells , Rv3615c 41-50 , and elicits CD4 + T-cell response with an effector-memory phenotype and multi-Th1-type cytokine coexpressions . Since T cells resident at mucosal tissue are potent at control of infection at early stage , our data show that intranasal immunization with Rv3615c promotes a sustained regional immunity to M.tb , and suggests a potency in control of M.tb infection . Our study warranties a further investigation of Rv3615c as a candidate for development of effective vaccination against M.tb infection . adaptive immunity , CD4 , intranasal , mucosal , Mycobacterium tuberculosis , Rv3615c , Th1\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Sustained adaptive immunity to pathogens provides effective protection against infections ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"and effector cells located at the site of infection ensure rapid response to the challenge .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Both are essential for the success of vaccine development .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"To explore new vaccination approach against Mycobacterium tuberculosis ( M.tb ) infection ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"we have shown that Rv3615c ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"identified as ESX-1 substrate protein C of M.tb but not expressed in BCG ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"induced a dominant Th1-type response of CD4 + T cells from patients with tuberculosis pleurisy ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"which suggests a potential candidate for vaccine development .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"But subcutaneous immunization with Rv3615c induced modest T-cell responses systemically ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"and showed suboptimal protection against virulent M.tb challenge at the site of infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Here , we use a mouse model to demonstrate that intranasal immunization with Rv3615c induces sustained capability of adaptive CD4 + T-and B-cell responses in lung parenchyma and airway .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Rv3615c contains a dominant epitope of mouse CD4 + T cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Rv3615c 41-50 , and elicits CD4 + T-cell\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"response with an effector-memory phenotype and multi-Th1-type cytokine coexpressions .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"Since T cells resident at mucosal tissue are potent at control of infection at early stage ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"our data show that intranasal immunization with Rv3615c promotes a sustained regional immunity to M.tb ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"and suggests a potency in control of M.tb infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Our study warranties a further investigation of Rv3615c as a candidate for development of effective vaccination against M.tb infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"adaptive immunity , CD4 , intranasal ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 19}, {\"segment_text\": \"mucosal , Mycobacterium tuberculosis , Rv3615c , Th1\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 20}]}"}]}
{"paper_id": "d29ac40afbb28f3dff1d4923aae6c01299399334", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nViral infection initiates an array of changes in host gene expression . Many viruses dampen host protein expression and attempt to evade the host anti-viral defense machinery . Host gene expression is suppressed at several stages of host messenger RNA ( mRNA ) formation including selective degradation of translationally competent messenger RNAs . Besides mRNAs , host cells also express a variety of noncoding RNAs , including small RNAs , that may also be subject to inhibition upon viral infection . In this review we focused on different ways viruses antagonize coding and noncoding RNAs in the host cell to its advantage .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Viral infection initiates an array of changes in host gene expression .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Many viruses dampen host protein expression and attempt to evade the host anti-viral defense machinery .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Host gene expression is suppressed at several stages of host messenger RNA ( mRNA ) formation including selective degradation of translationally competent messenger RNAs .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Besides mRNAs , host cells also express a variety of noncoding RNAs ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"including small RNAs , that may also be subject to inhibition upon viral infection .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"In this review we focused on different ways viruses antagonize coding and noncoding RNAs in the host cell to its advantage .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}]}"}]}
{"paper_id": "021aa59c28ff346dcdd67e70d20b4dc2af4bc3c9", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThis paper aims to give deeper insights into decision making problem based on interval-valued fuzzy soft set ( IVFSS ) . Firstly , a new score function for interval-valued fuzzy number is proposed for tackling the comparison problem . Subsequently , the formulae of information measures ( distance measure , similarity measure and entropy ) are introduced and their transformation relations are pioneered . Then , the objective weights of various parameters are determined via new entropy method , meanwhile , we develop the combined weights , which can show both the subjective information and the objective information . Moreover , we propose three algorithms to solve interval-valued fuzzy soft decision making problem by Weighted Distance Based Approximation ( WDBA ) , COmbinative Distance-based ASsessment ( CODAS ) and similarity measure . Finally , the effectiveness and feasibility of approaches are demonstrated by a mine emergency decision making problem . The salient features of the proposed methods , compared to the existing interval-valued fuzzy soft decision making methods , are ( 1 ) it can obtain the optimal alternative without counterintuitive phenomena ; ( 2 ) it has a great power in distinguishing the optimal alternative ; and ( 3 ) it can avoid the parameter selection problems .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"This paper aims to give deeper insights into decision making problem based on interval-valued fuzzy soft set ( IVFSS ) .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Firstly , a new score function for interval-valued fuzzy number is proposed for tackling the comparison problem .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"Subsequently , the formulae of information measures ( distance measure , similarity measure and entropy ) are introduced and their transformation relations are pioneered .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Then , the objective weights of various parameters are determined via new entropy method ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"meanwhile , we develop the combined weights ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"which can show both the subjective information and the objective information .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Moreover , we propose three algorithms to solve interval-valued fuzzy soft decision making problem by Weighted Distance Based Approximation ( WDBA ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"COmbinative Distance-based ASsessment ( CODAS ) and similarity measure .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Finally , the effectiveness and feasibility of approaches are demonstrated by a mine emergency decision making problem .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"The salient features of the proposed methods ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"compared to the existing interval-valued fuzzy soft decision making methods ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"are ( 1 ) it can obtain the optimal alternative without counterintuitive phenomena ; ( 2 ) it has a great power in distinguishing the optimal alternative ; and ( 3 ) it can avoid the parameter selection problems .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "2ed28b3c39080ffc7b75faa527b8b74b6253b45c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSevere acute respiratory syndrome coronavirus 2 ( SARS-CoV-2 ) is already responsible for far more deaths than previous pathogenic coronaviruses ( CoVs ) from 2002 and 2012 . The identification of clinically approved drugs to be repurposed to combat 2019 CoV disease ( COVID-19 ) would allow the rapid implementation of potentially lifesaving procedures . The major protease ( Mpro ) of SARS-CoV-2 is considered a promising target , based on previous results from related CoVs with lopinavir ( LPV ) , an HIV protease inhibitor . However , limited evidence exists for other clinically approved antiretroviral protease inhibitors , such as atazanavir ( ATV ) . ATV is of high interest because of its bioavailability within the respiratory tract . Our results show that ATV could dock in the active site of SARS-CoV-2 Mpro , with greater strength than LPV . ATV blocked Mpro activity . We confirmed that ATV inhibits SARS-CoV-2 replication , alone or in combination with ritonavir ( RTV ) in Vero cells , human pulmonary epithelial cell line and primary monocytes , impairing virus-induced enhancement of IL-6 and\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Severe acute respiratory syndrome coronavirus 2 ( SARS-CoV-2 ) is already responsible for far more deaths than previous pathogenic coronaviruses ( CoVs ) from 2002 and 2012 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"The identification of clinically approved drugs to be repurposed to combat 2019 CoV disease ( COVID-19 ) would allow the rapid implementation of potentially lifesaving procedures .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The major protease ( Mpro ) of SARS-CoV-2 is considered a promising target ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"based on previous results from related CoVs with lopinavir ( LPV ) , an HIV protease inhibitor .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"However , limited evidence exists for other clinically approved antiretroviral protease inhibitors ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"such as atazanavir ( ATV ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"ATV is of high interest because of its bioavailability within the respiratory tract .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Our results show that ATV could dock in the active site of SARS-CoV-2 Mpro ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"with greater strength than LPV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"ATV blocked Mpro activity .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"We confirmed that ATV inhibits SARS-CoV-2 replication ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"alone or in combination with ritonavir ( RTV ) in Vero cells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"human pulmonary epithelial cell line and primary monocytes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"impairing virus-induced enhancement of IL-6 and\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}]}"}]}
{"paper_id": "68c8bbbd6552e0ee02caea62c86752af5ef8d29d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nOne of the main tasks in biological sequence analysis is biological sequence comparison . Numerous efficient methods have been developed for sequence comparison . Traditional sequence comparison is based on sequence alignment . In this report , we propose a novel alignment-free method based on the relative Lempel-Ziv complexity to compare biological sequences . The vertebrate transferring genomes and the spike protein sequences are prepared and tested to evaluate the validity of the method . We use this method to build phylogenetic tree of two groups of the sequences . The result demonstrates that our method is powerful and efficient .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"One of the main tasks in biological sequence analysis is biological sequence comparison .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Numerous efficient methods have been developed for sequence comparison .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Traditional sequence comparison is based on sequence alignment .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"In this report , we propose a novel alignment-free method based on the relative Lempel-Ziv complexity to compare biological sequences .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"The vertebrate transferring genomes and the spike protein sequences are prepared and tested to evaluate the validity of the method .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"We use this method to build phylogenetic tree of two groups of the sequences .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"The result demonstrates that our method is powerful and efficient .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}]}"}]}
{"paper_id": "5738aa0be9b2dd358a1a968f90fad4b0723328f0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nObjective : Garlic is a plant has been used as a flavor , and antimicrobial and anti-diarrheal agent . Infectious bronchitis virus ( IBV ) is a coronavirus . The available vaccines against IBV can not cover new variants . This study evaluated the inhibitory effects of garlic extract on IBV . Materials and Methods : The constituents of garlic extract were detected by gas chromatography . This study was done in four groups of embryonic SPF eggs ; first group was used for virus titration ; second group received the mixture of different virus titration and constant amount of garlic extract ; third group received 10 -3 titration of virus and after 8 hr received garlic extract and the last group received different dilutions of garlic extract . Results : Based on our results , in the second group , IBV vaccine strain ( 4/91 ) at all titration and M41 in 10 -2 and 10 -3 titration and in the third group both variants of virus the embryonic Index ( EI ) was significantly increased . Conclusion : The garlic extract had inhibitory effects on IBV in the chickens embryo . Please cite this paper as Mohajer Shojai T , Ghalyanchi Langeroudi A , Karimi V , Barin A , Sadri N . The Effect of Allium sativum ( Garlic ) extract on infectious bronchitis virus in specific pathogen free embryonic egg . Avicenna J Phytomed , 2016 ; 6 ( 4 ) : 458-467 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Objective : Garlic is a plant has been used as a flavor ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"and antimicrobial and anti-diarrheal agent .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Infectious bronchitis virus ( IBV ) is a coronavirus .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The available vaccines against IBV can not cover new variants .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"This study evaluated the inhibitory effects of garlic extract on IBV .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"Materials and Methods : The constituents of garlic extract were detected by gas chromatography .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"This study was done in four groups of embryonic SPF eggs ; first group was used for virus titration ; second group received the mixture of different virus titration and constant amount of garlic extract ; third group received 10 -3 titration of virus and after 8 hr received garlic extract and the last group received different dilutions of garlic extract .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Results : Based on our results ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"in the second group , IBV vaccine strain ( 4/91 ) at all titration and M41 in 10 -2 and 10 -3 titration and in the third group both variants of virus the embryonic Index ( EI ) was significantly increased .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Conclusion : The garlic extract had inhibitory effects on IBV in the chickens embryo .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Please cite this paper as Mohajer Shojai T ,\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 11}, {\"segment_text\": \"Ghalyanchi Langeroudi A , Karimi V ,\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 12}, {\"segment_text\": \"Barin A , Sadri N .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 13}, {\"segment_text\": \"The Effect of Allium sativum ( Garlic ) extract on infectious bronchitis virus in specific pathogen free embryonic egg .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 14}, {\"segment_text\": \"Avicenna J Phytomed , 2016 ; 6 ( 4 ) : 458-467 .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 15}]}"}]}
{"paper_id": "5377df0dc057949f0124019cf03976cc495bb97d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nTourism resources are the prerequisite and basis for urban tourism development . Unlike mineral products and oil , tourism resources are renewable . How to find , create , manage , and maintain urban tourism resources will determine if they can be used sustainably . As the traditional coastal tourist city of China , Weihai does not have obvious advantages compared with other areas , so Weihai should develop a new tourism resource , an ` exotic culture ' resource , offered by regional advantage . The paper will explore the feasibility of developing an ` exotic culture ' resource for Weihai tourism in order to fulfil the sustainable utilization and development of tourism resources .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Tourism resources are the prerequisite and basis for urban tourism development .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Unlike mineral products and oil , tourism resources are renewable .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"How to find , create ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"manage , and maintain urban tourism resources will determine if they can be used sustainably .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"As the traditional coastal tourist city of China ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Weihai does not have obvious advantages compared with other areas ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"so Weihai should develop a new tourism resource ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"an ` exotic culture ' resource , offered by regional advantage .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"The paper will explore the feasibility of developing an ` exotic culture ' resource for Weihai tourism in order to fulfil the sustainable utilization and development of tourism resources .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}]}"}]}
{"paper_id": "c8b4daf8243b1b473ed0cb99ce033a00f2d6692f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nWe have investigated the role of two polymorphic sites ( R190W and N192K ) on the binding and activation of the formyl peptide receptor ( FPR ) by viral and formyl peptides . WEDWVGWI , a peptide with antiviral activity derived from the membrane proximal region of feline immunodeficiency virus , binds with high affinity to FPR . The three tryptophans in the peptide are all essential for FPR binding , just as they were essential for antiviral activity ( S. Giannecchini , A. Di Fenza , A.M. D'Ursi , D. Matteucci , P. Rovero , M. Bendinelli , Antiviral activity and conformational features of an octapeptide derived from the membrane-proximal ectodomain of the feline immunodeficiency virus transmembrane glycoprotein , J. Virol . 77 ( 2003 ) 3724 ) . Formyl-NleWEDWVGWI behaved as a weak partial agonist with FPR W190/N192 but a stronger partial agonist with FPR R190/K192 and FPR R190/N192 . Formyl-NleNleWEDWVGWI behaved as a full agonist toward all three FPRs but exhibited a much higher EC 50 with W190/N192 FPR ( 300 ± 45 nM ) than for R190/K192 FPR ( 40 ± 3 nM ) or R190/N192 ( 60 ± 8 nM ) . Formyl-MYKWPWYVWL preferentially activated R190/K192 and R190/N192 FPRs by N 5 fold compared to W190/N192 FPR . Formyl-MFEDAVAWF , a peptide derived from a protein in Mycobacterium avium subsp. paratuberculosis and formyl-MFTFEPFPTN , a peptide derived from the N-terminus of chemotaxis inhibitory protein of Staphylococcus aureus with an added N-terminal formyl-methionine exhibited the greatest selectivity for R190/K192 and R190/N192 FPRs with ∼ 10 fold lower EC 50 s than that observed with FPR W190/N192 . Thus , individuals with the W190 polymorphism may display a reduced ability to detect certain formyl peptides .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"We have investigated the role of two polymorphic sites ( R190W and N192K ) on the binding and activation of the formyl peptide receptor ( FPR ) by viral and formyl peptides .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"WEDWVGWI , a peptide with antiviral activity derived from the membrane proximal region of feline immunodeficiency virus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"binds with high affinity to FPR .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"The three tryptophans in the peptide are all essential for FPR binding ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"just as they were essential for antiviral activity ( S. Giannecchini , A. Di Fenza , A.M. D'Ursi , D. Matteucci , P. Rovero , M. Bendinelli , Antiviral activity and conformational features of an octapeptide derived from the membrane-proximal ectodomain of the feline immunodeficiency virus transmembrane glycoprotein , J. Virol .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"77 ( 2003 ) 3724 ) .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 6}, {\"segment_text\": \"Formyl-NleWEDWVGWI behaved as a weak partial agonist with FPR W190/N192 but a stronger partial agonist with FPR R190/K192 and FPR R190/N192 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Formyl-NleNleWEDWVGWI behaved as a full agonist toward all three FPRs but exhibited a much higher EC 50 with W190/N192 FPR ( 300 ± 45 nM ) than for R190/K192 FPR ( 40 ± 3 nM ) or R190/N192 ( 60 ± 8 nM ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Formyl-MYKWPWYVWL preferentially activated R190/K192 and R190/N192 FPRs by N 5 fold compared to W190/N192 FPR .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Formyl-MFEDAVAWF , a peptide derived from a protein in Mycobacterium avium subsp. paratuberculosis and formyl-MFTFEPFPTN ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"a peptide derived from the N-terminus of chemotaxis inhibitory protein of Staphylococcus aureus with an added N-terminal formyl-methionine exhibited the greatest selectivity for R190/K192 and R190/N192 FPRs with ∼ 10 fold lower EC 50 s than that observed with FPR W190/N192 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Thus , individuals with the W190 polymorphism may display a reduced ability to detect certain formyl peptides .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "725984c84bc703a34bc290f897e9f411ba3a67ec", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe transmission of infectious microbes via bioaerosols is of significant concern for both human and animal health . However , gaps in our understanding of respiratory pathogen transmission and methodological heterogeneity persist . New developments have enabled progress in this domain , and one of the major turning points has been the recognition that cross-disciplinary collaborations across spheres of human and animal health , microbiology , biophysics , engineering , aerobiology , infection control , public health , occupational health , and industrial hygiene are essential . Collaborative initiatives support advances in topics such as bioaerosol behavior , dispersion models , risk assessment , risk/exposure effects , and mitigation strategies in clinical , experimental , agricultural , and other field settings . There is a need to enhance the knowledge translation for researchers , stakeholders , and private partners to support a growing network of individuals and agencies to achieve common goals to mitigate inter-and intra-species pathogen transmission via bioaerosols .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The transmission of infectious microbes via bioaerosols is of significant concern for both human and animal health .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"However , gaps in our understanding of respiratory pathogen transmission and methodological heterogeneity persist .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"New developments have enabled progress in this domain ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"and one of the major turning points has been the recognition that cross-disciplinary collaborations across spheres of human and animal health ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"microbiology , biophysics , engineering ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"aerobiology , infection control , public health ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"occupational health , and industrial hygiene are essential .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Collaborative initiatives support advances in topics such as bioaerosol behavior ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"dispersion models , risk assessment ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"risk/exposure effects , and mitigation strategies in clinical ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"experimental , agricultural , and other field settings .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"There is a need to enhance the knowledge translation for researchers ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}, {\"segment_text\": \"stakeholders , and private partners to support a growing network of individuals and agencies to achieve common goals to mitigate inter-and intra-species pathogen transmission via bioaerosols .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 13}]}"}]}
{"paper_id": "9a5586078edf5a43100db04f987d635d39fee4a5", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Longtime follow-up studies on patients with pharyngotonsillitis are rare . We aimed to describe the patterns of new visits for a sore throat , complications and tonsillectomy during 2 years in a cohort of patients with pharyngotonsillitis and non-infected controls . Methods : A retrospective chart review was performed on a cohort of patients with acute sore throat ( n = 207 ) , and non-infected controls ( n = 108 ) . New visits , complications and tonsillectomy within 2 years was recorded and analyzed in relation to microbiological findings at inclusion . Results : Patients with Group A streptococci ( GAS ) ( 12/66 ) reconsulted more often within 30 days than patients with no GAS ( 9/141 ) ( p = 0.009 ) and patients with F. necrophorum ( 2/29 ) . After 2 years , we observed no significant differences in reconsultations with regard to aetiology at inclusion . A single complication was recorded and 5 patients were planned for tonsillectomy . Conclusions : Group A streptococci were the sole aetiological agent associated with recurrent sore throat while F. necrophorum did not distinguish itself as a major cause of either recurrent infection or complications in this cohort . More studies , preferably with the focus on adolescents , are needed before F. necrophorum can be considered an important cause of pharyngotonsillitis .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Longtime follow-up studies on patients with pharyngotonsillitis are rare .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"We aimed to describe the patterns of new visits for a sore throat ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"complications and tonsillectomy during 2 years in a cohort of patients with pharyngotonsillitis and non-infected controls .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"Methods : A retrospective chart review was performed on a cohort of patients with acute sore throat ( n = 207 ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"and non-infected controls ( n = 108 ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"New visits , complications and tonsillectomy within 2 years was recorded and analyzed in relation to microbiological findings at inclusion .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Results : Patients with Group A streptococci ( GAS ) ( 12/66 ) reconsulted more often within 30 days than patients with no GAS ( 9/141 ) ( p = 0.009 ) and patients with F. necrophorum ( 2/29 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"After 2 years , we observed no significant differences in reconsultations with regard to aetiology at inclusion .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"A single complication was recorded and 5 patients were planned for tonsillectomy .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Conclusions : Group A streptococci were the sole aetiological agent associated with recurrent sore throat while F. necrophorum did not distinguish itself as a major cause of either recurrent infection or complications in this cohort .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"More studies , preferably with the focus on adolescents ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"are needed before F. necrophorum can be considered an important cause of pharyngotonsillitis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "e92e2d8ab6aedfa9c7486162c9520e4ea4485df2", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe majority of human emerging infectious diseases ( EIDs ) are zoonotic , with viruses originating in wild mammals of particular concern ( e.g. HIV , Ebola , SARS ) 1-3 . Understanding patterns of viral diversity in wildlife and determinants of successful cross-species transmission , or spillover , are therefore key goals for pandemic surveillance programs 4 . However , few analytical tools exist to identify which host species likely harbor the next human virus , or which viruses can cross species boundaries 5-7 . Here we conduct the most comprehensive analysis yet of mammalian hostvirus relationships and show that both the total number of viruses that infect a given species , and the proportion likely to be zoonotic are predictable . After controlling for research effort , the proportion of zoonotic viruses per species is predicted by phylogenetic relatedness to humans , host taxonomy , and human population within a species range - which may reflect human-wildlife contact . We demonstrate for the first time that bats harbor a significantly higher proportion of zoonotic viruses than all other mammalian orders . We identify the taxa and geographic regions with the largest estimated number of ` missing viruses ' and ` missing zoonoses ' and therefore of highest value for future surveillance . We then show that phylogenetic host breadth and other viral traits are significant predictors of zoonotic potential , providing a novel framework to assess if a newly discovered mammalian virus could infect people . Viral zoonoses are a serious threat to public health and global security , and have caused the majority of recent pandemics in people 4 , yet our understanding of the factors driving viral diversity in mammals , viral host range , and cross-species transmission to humans remain nascent . Recent studies have described broad patterns of pathogen host range 1,3 and various host or microbial factors that facilitate cross-species transmission 5,7,8 , or have focused on Users may view , print , copy , and download text and data-mine the content in such documents , for the purposes of academic research , subject always to the full Conditions of use : http://www.nature . All datasets ( host traits , viral traits , full list of host-virus associations and associated references , phylogenetic trees , and phylogenetic distance matrices ) along with the R code and R package dependencies needed to fully replicate and evaluate these analyses are provided at http://doi.org/10.5281/zenodo.569079 . The top-level README.txt file in the directory details the file structure and metadata provided .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The majority of human emerging infectious diseases ( EIDs ) are zoonotic ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"with viruses originating in wild mammals of particular concern ( e.g. HIV , Ebola , SARS ) 1-3 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Understanding patterns of viral diversity in wildlife and determinants of successful cross-species transmission ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"or spillover , are therefore key goals for pandemic surveillance programs 4 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"However , few analytical tools exist to identify which host species likely harbor the next human virus ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"or which viruses can cross species boundaries 5-7 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Here we conduct the most comprehensive analysis yet of mammalian hostvirus relationships and show that both the total number of viruses that infect a given species ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"and the proportion likely to be zoonotic are predictable .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"After controlling for research effort ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"the proportion of zoonotic viruses per species is predicted by phylogenetic relatedness to humans ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"host taxonomy , and human population within a species range - which may reflect human-wildlife contact .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"We demonstrate for the first time that bats harbor a significantly higher proportion of zoonotic viruses than all other mammalian orders .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"We identify the taxa and geographic regions with the largest estimated number of ` missing viruses ' and ` missing zoonoses ' and therefore of highest value for future surveillance .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"We then show that phylogenetic host breadth and other viral traits are significant predictors of zoonotic potential ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"providing a novel framework to assess if a newly discovered mammalian virus could infect people .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Viral zoonoses are a serious threat to public health and global security ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 16}, {\"segment_text\": \"and have caused the majority of recent pandemics in people 4 ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 17}, {\"segment_text\": \"yet our understanding of the factors driving viral diversity in mammals ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 18}, {\"segment_text\": \"viral host range , and cross-species transmission to humans remain nascent .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 19}, {\"segment_text\": \"Recent studies have described broad patterns of pathogen host range 1,3 and various host or microbial factors that facilitate cross-species transmission 5,7,8 ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 20}, {\"segment_text\": \"or have focused on Users may view ,\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 21}, {\"segment_text\": \"print , copy , and download text and data-mine the content in such documents ,\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 22}, {\"segment_text\": \"for the purposes of academic research ,\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 23}, {\"segment_text\": \"subject always to the full Conditions of use : http://www.nature .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 24}, {\"segment_text\": \"All datasets ( host traits , viral traits , full list of host-virus associations and associated references , phylogenetic trees , and phylogenetic distance matrices ) along with the R code and R package dependencies needed to fully replicate and evaluate these analyses are provided at http://doi.org/10.5281/zenodo.569079 .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 25}, {\"segment_text\": \"The top-level README.txt file in the directory details the file structure and metadata provided .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 26}]}"}]}
{"paper_id": "f0813fe3f70fb9a52ec5944b43bdd953a08cc49a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe location of autocrine interactions between the v-sis protein and PDGF receptors remains uncertain and controversial . To examine whether receptor-ligand interactions can occur intracellularly , we have constructed fusion proteins that anchor v-sis to specific intracellular membranes . Fusion of a cis-Golgi retention signal from a coronavirus E1 glycoprotein to v-sis protein completely abolished its transforming ability when transfected into NIH3T3 cells . Fusion proteins incorporating mutations in this retention signal were not retained within the Golgi complex but instead were transported to the cell surface , resulting in efficient transformation . All chimeric proteins were shown to dimerize properly . Derivatives of some of these constructs were also constructed bearing the cytoplasmic tail from the glycoprotein of vesicular stomatitis virus ( VSV-G ) . These constructs allowed examination of subcellular localization by double-label immunofluorescence , using antibodies that distinguish between the extraceUular PDGF-related domain and the VSV-G cytoplasmic tail . Colocalization of sis-E1-G with Golgi markers confirmed its targeting to the early Golgi complex . The sis-E1 constructs , targeted to the early Golgi complex , exhibited no proteo-lyric processing whereas the mutant forms of sis-E1 exhibited normal proteolytic processing . Treatment with suramin , a polyanionic compound that disrupts ligand/receptor interactions at the cell surface , was able to revert the transformed phenotype induced by the mutant sis-E1 constructs described here . Our results demonstrate that autocrine interactions between the v-sis oncoprotein and PDGF receptors within the early Golgi complex do not result in functional signal transduction . Another v-sis fusion protein was constructed by attaching the transmembrane domain and COOHterminus of TGN38 , a protein that localizes to the trans-Golgi network ( TGN ) . This construct was primarily retained intracellularly , although some of the fusion protein reached the surface . Deletion of the COOH-terminal region of the TGN38 retention signal abrogated the TGN-localization , as evidenced by very prominent cell surface localization , and resulted in increased transforming activity . The behavior of the sis-TGN38 derivatives is discussed within the context of the properties of TGN38 itself , which is known to recycle from the cell surface to the TGN .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The location of autocrine interactions between the v-sis protein and PDGF receptors remains uncertain and controversial .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"To examine whether receptor-ligand interactions can occur intracellularly ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"we have constructed fusion proteins that anchor v-sis to specific intracellular membranes .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Fusion of a cis-Golgi retention signal from a coronavirus E1 glycoprotein to v-sis protein completely abolished its transforming ability when transfected into NIH3T3 cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Fusion proteins incorporating mutations in this retention signal were not retained within the Golgi complex but instead were transported to the cell surface , resulting in efficient transformation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"All chimeric proteins were shown to dimerize properly .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Derivatives of some of these constructs were also constructed bearing the cytoplasmic tail from the glycoprotein of vesicular stomatitis virus ( VSV-G ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"These constructs allowed examination of subcellular localization by double-label immunofluorescence ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"using antibodies that distinguish between the extraceUular PDGF-related domain and the VSV-G cytoplasmic tail .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Colocalization of sis-E1-G with Golgi markers confirmed its targeting to the early Golgi complex .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The sis-E1 constructs , targeted to the early Golgi complex ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"exhibited no proteo-lyric processing whereas the mutant forms of sis-E1 exhibited normal proteolytic processing .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Treatment with suramin , a polyanionic compound that disrupts ligand/receptor interactions at the cell surface ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"was able to revert the transformed phenotype induced by the mutant sis-E1 constructs described here .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Our results demonstrate that autocrine interactions between the v-sis oncoprotein and PDGF receptors within the early Golgi complex do not result in functional signal transduction .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Another v-sis fusion protein was constructed by attaching the transmembrane domain and COOHterminus of TGN38 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"a protein that localizes to the trans-Golgi network ( TGN ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"This construct was primarily retained intracellularly ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"although some of the fusion protein reached the surface .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Deletion of the COOH-terminal region of the TGN38 retention signal abrogated the TGN-localization ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"as evidenced by very prominent cell surface localization ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"and resulted in increased transforming activity .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"The behavior of the sis-TGN38 derivatives is discussed within the context of the properties of TGN38 itself ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"which is known to recycle from the cell surface to the TGN .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}]}"}]}
{"paper_id": "cc39d839697c9a6791be6cdce7a556d8d1ed324c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nHuman adenoviral ( HAd ) vectors have demonstrated great potential as vaccine vectors . Preclinical and clinical studies have demonstrated the feasibility of vector design , robust antigen expression and protective immunity using this system . However , clinical use of adenoviral vectors for vaccine purposes is anticipated to be limited by vector immunity that is either preexisting or develops rapidly following the first inoculation with adenoviral vectors . Vector immunity inactivates the vector particles and rapidly removes the transduced cells , thereby limiting the duration of transgene expression . Due to strong vector immunity , subsequent use of the same vector is usually less efficient . In order to circumvent this limitation , nonhuman adenoviral vectors have been proposed as alternative vectors . In addition to eluding HAd immunity , these vectors possess most of the attractive features of HAd vectors . Several replication-competent or replication-defective nonhuman adenoviral vectors have been developed and investigated for their potential as vaccine delivery vectors . Here , we review recent advances in the design and characterization of various nonhuman adenoviral vectors , and discuss their potential applications for human and animal vaccination .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Human adenoviral ( HAd ) vectors have demonstrated great potential as vaccine vectors .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Preclinical and clinical studies have demonstrated the feasibility of vector design ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"robust antigen expression and protective immunity using this system .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"However , clinical use of adenoviral vectors for vaccine purposes is anticipated to be limited by vector immunity that is either preexisting or develops rapidly following the first inoculation with adenoviral vectors .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Vector immunity inactivates the vector particles and rapidly removes the transduced cells ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"thereby limiting the duration of transgene expression .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"Due to strong vector immunity ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"subsequent use of the same vector is usually less efficient .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"In order to circumvent this limitation ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"nonhuman adenoviral vectors have been proposed as alternative vectors .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"In addition to eluding HAd immunity ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"these vectors possess most of the attractive features of HAd vectors .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 12}, {\"segment_text\": \"Several replication-competent or replication-defective nonhuman adenoviral vectors have been developed and investigated for their potential as vaccine delivery vectors .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 13}, {\"segment_text\": \"Here , we review recent advances in the design and characterization of various nonhuman adenoviral vectors ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 14}, {\"segment_text\": \"and discuss their potential applications for human and animal vaccination .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 15}]}"}]}
{"paper_id": "120138f6ef07fac0c75d777ffb9946480f613065", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nNeuropathic pain is among the most debilitating forms of chronic pain . Studies have suggested that chronic pain pathogenesis involves neuroimmune interactions and blood-spinal cord barrier ( BSCB ) disruption . However , the underlying mechanisms are poorly understood . We modeled neuropathic pain in rats by inducing chronic constriction injury ( CCI ) of the sciatic nerve and analyzed the effects on C-X-C motif chemokine 10 ( CXCL10 ) / CXCR3 activation , BSCB permeability , and immune cell migration from the circulation into the spinal cord . We detected CXCR3 expression in spinal neurons and observed that CCI induced CXCL10/CXCR3 activation , BSCB disruption , and mechanical hyperalgesia . CCI-induced BSCB disruption enabled circulating T cells to migrate into the spinal parenchyma . Intrathecal administration of an anti-CXCL10 antibody not only attenuated CCI-induced hyperalgesia , but also reduced BSCB permeability , suggesting that CXCL10 acts as a key regulator of BSCB integrity . Moreover , T cell migration may play a critical role in the neuroimmune interactions involved in the pathogenesis of CCI-induced neuropathic pain . Our results highlight CXCL10 as a new potential drug target for the treatment of nerve injury-induced neuropathic pain .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Neuropathic pain is among the most debilitating forms of chronic pain .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Studies have suggested that chronic pain pathogenesis involves neuroimmune interactions and blood-spinal cord barrier ( BSCB ) disruption .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"However , the underlying mechanisms are poorly understood .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"We modeled neuropathic pain in rats by inducing chronic constriction injury ( CCI ) of the sciatic nerve and analyzed the effects on C-X-C motif chemokine 10 ( CXCL10 ) / CXCR3 activation ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"BSCB permeability , and immune cell migration from the circulation into the spinal cord .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"We detected CXCR3 expression in spinal neurons and observed that CCI induced CXCL10/CXCR3 activation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"BSCB disruption , and mechanical hyperalgesia .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"CCI-induced BSCB disruption enabled circulating T cells to migrate into the spinal parenchyma .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Intrathecal administration of an anti-CXCL10 antibody not only attenuated CCI-induced hyperalgesia ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"but also reduced BSCB permeability ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"suggesting that CXCL10 acts as a key regulator of BSCB integrity .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Moreover , T cell migration may play a critical role in the neuroimmune interactions involved in the pathogenesis of CCI-induced neuropathic pain .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Our results highlight CXCL10 as a new potential drug target for the treatment of nerve injury-induced neuropathic pain .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "2606e22c2560b4cc0909c102ee356d562d78a9f3", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIn viruses , programmed À1 ribosomal frameshifting ( À1 PRF ) signals direct the translation of alternative proteins from a single mRNA . Given that many basic regulatory mechanisms were first discovered in viral systems , the current study endeavored to : ( i ) identify À1 PRF signals in genomic databases , ( ii ) apply the protocol to the yeast genome and ( iii ) test selected candidates at the bench . Computational analyses revealed the presence of 10 340 consensus À1 PRF signals in the yeast genome . Of the 6353 yeast ORFs , 1275 contain at least one strong and statistically significant À1 PRF signal . Eight out of nine selected sequences promoted efficient levels of PRF in vivo . These findings provide a robust platform for high throughput computational and laboratory studies and demonstrate that functional À1 PRF signals are widespread in the genome of Saccharomyces cerevisiae . The data generated by this study have been deposited into a publicly available database called the PRFdb . The presence of stable mRNA pseudoknot structures in these À1 PRF signals , and the observation that the predicted outcomes of nearly all of these genomic frameshift signals would direct ribosomes to premature termination codons , suggest two possible mRNA destabilization pathways through which À1 PRF signals could post-transcriptionally regulate mRNA abundance .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"In viruses , programmed À1 ribosomal frameshifting ( À1 PRF ) signals direct the translation of alternative proteins from a single mRNA .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Given that many basic regulatory mechanisms were first discovered in viral systems ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"the current study endeavored to : ( i ) identify À1 PRF signals in genomic databases ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"( ii ) apply the protocol to the yeast genome and ( iii ) test selected candidates at the bench .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Computational analyses revealed the presence of 10 340 consensus À1 PRF signals in the yeast genome .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Of the 6353 yeast ORFs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"1275 contain at least one strong and statistically significant À1 PRF signal .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"Eight out of nine selected sequences promoted efficient levels of PRF in vivo .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"These findings provide a robust platform for high throughput computational and laboratory studies and demonstrate that functional À1 PRF signals are widespread in the genome of Saccharomyces cerevisiae .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"The data generated by this study have been deposited into a publicly available database called the PRFdb .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"The presence of stable mRNA pseudoknot structures in these À1 PRF signals ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"and the observation that the predicted outcomes of nearly all of these genomic frameshift signals would direct ribosomes to premature termination codons ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"suggest two possible mRNA destabilization pathways through which À1 PRF signals could post-transcriptionally regulate mRNA abundance .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "63008713691bdb1d8eed016dbc54332f11d43739", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Despite the seriousness of dengue-related disease , with an estimated 50-100 million cases of dengue fever and 250,000-500,000 cases of dengue hemorrhagic fever/dengue shock syndrome each year , a clear understanding of dengue pathogenesis remains elusive . Because of the lack of a disease model in animals and the complex immune interaction in dengue infection , the study of host response and immunopathogenesis is difficult . The development of genomics technology , microarray and high throughput quantitative PCR have allowed researchers to study gene expression changes on a much broader scale . We therefore used this approach to investigate the host response in dengue virusinfected cell lines and in patients developing dengue fever . Methodology/Principal Findings : Using microarray and high throughput quantitative PCR method to monitor the host response to dengue viral replication in cell line infection models and in dengue patient blood samples , we identified differentially expressed genes along three major pathways ; NF-kB initiated immune responses , type I interferon ( IFN ) and the ubiquitin proteasome pathway . Among the most highly upregulated genes were the chemokines IP-10 and I-TAC , both ligands of the CXCR3 receptor . Increased expression of IP-10 and I-TAC in the peripheral blood of ten patients at the early onset of fever was confirmed by ELISA . A highly upregulated gene in the IFN pathway , viperin , was overexpressed in A549 cells resulting in a significant reduction in viral replication . The upregulation of genes in the ubiquitin-proteasome pathway prompted the testing of proteasome inhibitors MG-132 and ALLN , both of which reduced viral replication . Conclusion/Significance : Unbiased gene expression analysis has identified new host genes associated with dengue infection , which we have validated in functional studies . We showed that some parts of the host response can be used as potential biomarkers for the disease while others can be used to control dengue viral replication , thus representing viable targets for drug therapy .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Despite the seriousness of dengue-related disease ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"with an estimated 50-100 million cases of dengue fever and 250,000-500,000 cases of dengue hemorrhagic fever/dengue shock syndrome each year ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"a clear understanding of dengue pathogenesis remains elusive .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Because of the lack of a disease model in animals and the complex immune interaction in dengue infection ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"the study of host response and immunopathogenesis is difficult .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"The development of genomics technology ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"microarray and high throughput quantitative PCR have allowed researchers to study gene expression changes on a much broader scale .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"We therefore used this approach to investigate the host response in dengue virusinfected cell lines and in patients developing dengue fever .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"Methodology/Principal Findings : Using microarray and high throughput quantitative PCR method to monitor the host response to dengue viral replication in cell line infection models and in dengue patient blood samples ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"we identified differentially expressed genes along three major pathways ; NF-kB initiated immune responses ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"type I interferon ( IFN ) and the ubiquitin proteasome pathway .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Among the most highly upregulated genes were the chemokines IP-10 and I-TAC ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"both ligands of the CXCR3 receptor .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"Increased expression of IP-10 and I-TAC in the peripheral blood of ten patients at the early onset of fever was confirmed by ELISA .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"A highly upregulated gene in the IFN pathway ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"viperin , was overexpressed in A549 cells resulting in a significant reduction in viral replication .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"The upregulation of genes in the ubiquitin-proteasome pathway prompted the testing of proteasome inhibitors MG-132 and ALLN ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 17}, {\"segment_text\": \"both of which reduced viral replication .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Conclusion/Significance : Unbiased gene expression analysis has identified new host genes associated with dengue infection ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 19}, {\"segment_text\": \"which we have validated in functional studies .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 20}, {\"segment_text\": \"We showed that some parts of the host response can be used as potential biomarkers for the disease while others can be used to control dengue viral replication ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 21}, {\"segment_text\": \"thus representing viable targets for drug therapy .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 22}]}"}]}
{"paper_id": "9fd83230962e678e8ec4d5dffee0bb431e19c2d9", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Numerous protocols for viral enrichment and genome amplification have been created . However , the direct identification of viral genomes from clinical specimens using next-generation sequencing ( NGS ) still has its challenges . As a selected viral nucleic acid extraction method may determine the sensitivity and reliability of NGS , it is still valuable to evaluate the extraction efficiency of different extraction kits using clinical specimens directly . Results : In this study , we performed qRT-PCR and viral metagenomic analysis of the extraction efficiency of four commonly used Qiagen extraction kits : QIAamp Viral RNA Mini Kit ( VRMK ) , QIAamp MinElute Virus Spin Kit ( MVSK ) , RNeasy Mini Kit ( RMK ) , and RNeasy Plus Micro Kit ( RPMK ) , using a mixed respiratory clinical sample without any pre-treatment . This sample contained an adenovirus ( ADV ) , influenza virus A ( Flu A ) , human parainfluenza virus 3 ( PIV3 ) , human coronavirus OC43 ( OC43 ) , and human metapneumovirus ( HMPV ) . The quantity and quality of the viral extracts were significantly different among these kits . The highest threshold cycle ( Ct ) values for ADV and OC43 were obtained by using the RPMK . The MVSK had the lowest Ct values for ADV and PIV3 . The RMK revealed the lowest detectability for HMPV and PIV3 . The most effective rate of NGS data at 67.47 % was observed with the RPMK . The other three kits ranged between 12.1-26.79 % effectiveness rates for the NGS data . Most importantly , compared to the other three kits the highest proportion of nonhost reads was obtained by the RPMK . The MVSK performed best with the lowest Ct value of 20.5 in the extraction of ADV , while the RMK revealed the best extraction efficiency by NGS analysis . Conclusions : The evaluation of viral nucleic acid extraction efficiency is different between NGS and qRT-PCR analysis . The RPMK was most applicable for the metagenomic analysis of viral RNA and enabled more sensitive identification of the RNA virus genome in respiratory clinical samples . In addition , viral RNA extraction kits were also applicable for metagenomic analysis of the DNA virus . Our results highlighted the importance of nucleic acid extraction kit selection , which has a major impact on the yield and number of viral reads by NGS analysis . Therefore , the choice of extraction method for a given viral pathogen needs to be carefully considered .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Numerous protocols for viral enrichment and genome amplification have been created .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"However , the direct identification of viral genomes from clinical specimens using next-generation sequencing ( NGS ) still has its challenges .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"As a selected viral nucleic acid extraction method may determine the sensitivity and reliability of NGS ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"it is still valuable to evaluate the extraction efficiency of different extraction kits using clinical specimens directly .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Results : In this study ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"we performed qRT-PCR and viral metagenomic analysis of the extraction efficiency of four commonly used Qiagen extraction kits : QIAamp Viral RNA Mini Kit ( VRMK ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"QIAamp MinElute Virus Spin Kit ( MVSK ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"RNeasy Mini Kit ( RMK ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and RNeasy Plus Micro Kit ( RPMK ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"using a mixed respiratory clinical sample without any pre-treatment .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"This sample contained an adenovirus ( ADV ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"influenza virus A ( Flu A ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"human parainfluenza virus 3 ( PIV3 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"human coronavirus OC43 ( OC43 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"and human metapneumovirus ( HMPV ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"The quantity and quality of the viral extracts were significantly different among these kits .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"The highest threshold cycle ( Ct ) values for ADV and OC43 were obtained by using the RPMK .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"The MVSK had the lowest Ct values for ADV and PIV3 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"The RMK revealed the lowest detectability for HMPV and PIV3 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"The most effective rate of NGS data at 67.47 % was observed with the RPMK .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"The other three kits ranged between 12.1-26.79 % effectiveness rates for the NGS data .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"Most importantly , compared to the other three kits the highest proportion of nonhost reads was obtained by the RPMK .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"The MVSK performed best with the lowest Ct value of 20.5 in the extraction of ADV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"while the RMK revealed the best extraction efficiency by NGS analysis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}, {\"segment_text\": \"Conclusions : The evaluation of viral nucleic acid extraction efficiency is different between NGS and qRT-PCR analysis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 25}, {\"segment_text\": \"The RPMK was most applicable for the metagenomic analysis of viral RNA and enabled more sensitive identification of the RNA virus genome in respiratory clinical samples .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 26}, {\"segment_text\": \"In addition , viral RNA extraction kits were also applicable for metagenomic analysis of the DNA virus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 27}, {\"segment_text\": \"Our results highlighted the importance of nucleic acid extraction kit selection ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 28}, {\"segment_text\": \"which has a major impact on the yield and number of viral reads by NGS analysis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 29}, {\"segment_text\": \"Therefore , the choice of extraction method for a given viral pathogen needs to be carefully considered .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 30}]}"}]}
{"paper_id": "3c440b07b2bc59e8483537e994bbd7ac0030801a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe establishment of persistent viral infection is often associated with the selection of one or more mutant viruses . For example , it has been found that an intraleader open reading frame ( ORF ) in genomic and subgenomic mRNA ( sgmRNA ) molecules is selected during bovine coronavirus ( BCoV ) persistence which leads to translation attenuation of the downstream ORF . Here , we report the unexpected identification of leaderless genomes , in addition to leader-containing genomes , in a cell culture persistently infected with BCoV . The discovery was made by using a head-to-tail ligation method that examines genomic 59-terminal sequences at different times postinfection . Functional analyses of the leaderless genomic RNA in a BCoV defective interfering ( DI ) RNA revealed that ( 1 ) the leaderless genome was able to serve as a template for the synthesis of negative-strand genome , although it can not perform replicative positive-strand genomic RNA synthesis , and ( 2 ) the leaderless genome retained its function in translation and transcription , although the efficiency of these processes was impaired . Therefore , this previously unidentified leaderless genome is associated with the attenuation of genome expression . Whether the leaderless genome contributes to the establishment of persistent infection remains to be determined .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The establishment of persistent viral infection is often associated with the selection of one or more mutant viruses .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"For example , it has been found that an intraleader open reading frame ( ORF ) in genomic and subgenomic mRNA ( sgmRNA ) molecules is selected during bovine coronavirus ( BCoV ) persistence which leads to translation attenuation of the downstream ORF .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Here , we report the unexpected identification of leaderless genomes ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"in addition to leader-containing genomes ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"in a cell culture persistently infected with BCoV .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"The discovery was made by using a head-to-tail ligation method that examines genomic 59-terminal sequences at different times postinfection .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Functional analyses of the leaderless genomic RNA in a BCoV defective interfering ( DI ) RNA revealed that ( 1 ) the leaderless genome was able to serve as a template for the synthesis of negative-strand genome ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"although it can not perform replicative positive-strand genomic RNA synthesis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and ( 2 ) the leaderless genome retained its function in translation and transcription ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"although the efficiency of these processes was impaired .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Therefore , this previously unidentified leaderless genome is associated with the attenuation of genome expression .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Whether the leaderless genome contributes to the establishment of persistent infection remains to be determined .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "3028628066ec2401f3981f4e70c5b1acd4cef573", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : As the COVID-19 epidemic is spreading , incoming data allows us to quantify values of key variables that determine the transmission and the effort required to control the epidemic . We determine the incubation period and serial interval distribution for transmission clusters in Singapore and in Tianjin . We infer the basic reproduction number and identify the extent of pre-symptomatic transmission . Methods : We collected outbreak information from Singapore and Tianjin , China , reported from Jan.19-Feb.26 and Jan.21-Feb.27 , respectively . We estimated incubation periods and serial intervals in both populations . Results : The mean incubation period was 7.1 ( 6.13 , 8.25 ) days for Singapore and 9 ( 7.92 , 10.2 ) days for Tianjin . Both datasets had shorter incubation periods for earlier-occurring cases . The mean serial interval was 4.56 ( 2.69 , 6.42 ) days for Singapore and 4.22 ( 3.43 , 5.01 ) for Tianjin . We inferred that early in the outbreaks , infection was transmitted on average 2.55 and 2.89 days before symptom onset ( Singapore , Tianjin ) . The estimated basic reproduction number for Singapore was 1.97 ( 1.45 , 2.48 ) secondary cases per infective ; for Tianjin it was 1.87 ( 1.65 , 2.09 ) secondary cases per infective . Conclusions : Estimated serial intervals are shorter than incubation periods in both Singapore and Tianjin , suggesting that pre-symptomatic transmission is occurring . Shorter serial intervals lead to lower estimates of R0 , which suggest that half of all secondary infections should be prevented to control spread .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : As the COVID-19 epidemic is spreading ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"incoming data allows us to quantify values of key variables that determine the transmission and the effort required to control the epidemic .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"We determine the incubation period and serial interval distribution for transmission clusters in Singapore and in Tianjin .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"We infer the basic reproduction number and identify the extent of pre-symptomatic transmission .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Methods : We collected outbreak information from Singapore and Tianjin ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"China , reported from Jan.19-Feb.26 and Jan.21-Feb.27 , respectively .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"We estimated incubation periods and serial intervals in both populations .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Results : The mean incubation period was 7.1 ( 6.13 , 8.25 ) days for Singapore and 9 ( 7.92 , 10.2 ) days for Tianjin .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"Both datasets had shorter incubation periods for earlier-occurring cases .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"The mean serial interval was 4.56 ( 2.69 , 6.42 ) days for Singapore and 4.22 ( 3.43 , 5.01 ) for Tianjin .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"We inferred that early in the outbreaks ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"infection was transmitted on average 2.55 and 2.89 days before symptom onset ( Singapore , Tianjin ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"The estimated basic reproduction number for Singapore was 1.97 ( 1.45 , 2.48 ) secondary cases per infective ; for Tianjin it was 1.87 ( 1.65 , 2.09 ) secondary cases per infective .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"Conclusions : Estimated serial intervals are shorter than incubation periods in both Singapore and Tianjin ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"suggesting that pre-symptomatic transmission is occurring .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"Shorter serial intervals lead to lower estimates of R0 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"which suggest that half of all secondary infections should be prevented to control spread .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}]}"}]}
{"paper_id": "395b2a804c283cbe6043584730841db6e87504ed", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPatients with highly infectious diseases require safe , secure , high-quality medical care with high-level infection control , which may be most eff ectively delivered by specially trained staff in the setting of a high-level isolation unit ( HLIU ) . The European Network of Infectious Diseases is a European Commission co-funded network of experts in the management of highly infectious diseases from national ( or regional ) centres designated for the care of this patient population . Participants took a consensus-based approach to develop a framework for the design and operation of HLIUs in Europe , covering clinical care provision , diagnostic services , transport , health and safety , and essential design and construction features , to support planning by health authorities for the safe and eff ective management of highly infectious diseases and preparedness for infectious disease emergencies in Europe .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Patients with highly infectious diseases require safe ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"secure , high-quality medical care with high-level infection control ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"which may be most eff ectively delivered by specially trained staff in the setting of a high-level isolation unit ( HLIU ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The European Network of Infectious Diseases is a European Commission co-funded network of experts in the management of highly infectious diseases from national ( or regional ) centres designated for the care of this patient population .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Participants took a consensus-based approach to develop a framework for the design and operation of HLIUs in Europe ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"covering clinical care provision , diagnostic services ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"transport , health and safety ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"and essential design and construction features ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"to support planning by health authorities for the safe and eff ective management of highly infectious diseases and preparedness for infectious disease emergencies in Europe .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}]}"}]}
{"paper_id": "41ed8edac17db0256c043cee4b27884395539746", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe cure effect of a virus model with both cell-to-cell transmission and cell-to-virus transmission is studied . By the method of next generation matrix , the basic reproduction number is obtained . The locally asymptotic stability of the virus-free equilibrium and the endemic equilibrium is considered by investigating the characteristic equation of the model . The globally asymptotic stability of the virus-free equilibrium is proved by constructing suitable Lyapunov function , and the sufficient condition for the globally asymptotic stability of the endemic equilibrium is obtained by constructing suitable Lyapunov function and using LaSalle invariance principal .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The cure effect of a virus model with both cell-to-cell transmission and cell-to-virus transmission is studied .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"By the method of next generation matrix ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"the basic reproduction number is obtained .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"The locally asymptotic stability of the virus-free equilibrium and the endemic equilibrium is considered by investigating the characteristic equation of the model .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"The globally asymptotic stability of the virus-free equilibrium is proved by constructing suitable Lyapunov function ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"and the sufficient condition for the globally asymptotic stability of the endemic equilibrium is obtained by constructing suitable Lyapunov function and using LaSalle invariance principal .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}]}"}]}
{"paper_id": "ccfde92cc14959cab65169629c83390d9b9c7794", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nconsider the wider repercussions of their actions . It is accepted that in an ecological system , pressure will cause evolution ; this is also the case with antimicrobials , the result being the development of resistance and the therapeutic failure of drugs . To an extent , this can be ameliorated through advances by the pharmaceutical industry , but that should not stop us from critically appraising our use and modifying our behavior to slow this process down .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"consider the wider repercussions of their actions .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"It is accepted that in an ecological system ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"pressure will cause evolution ; this is also the case with antimicrobials ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"the result being the development of resistance and the therapeutic failure of drugs .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"To an extent , this can be ameliorated through advances by the pharmaceutical industry ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"but that should not stop us from critically appraising our use and modifying our behavior to slow this process down .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}]}"}]}
{"paper_id": "73fcc68f1fe5bf9cae21d939f459968ebed64411", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe liver-specific microRNA miR-122 , which has essential roles in liver development and metabolism , is a key proviral factor for hepatitis C virus ( HCV ) . Despite its crucial role in the liver and HCV life cycle , little is known about the molecular mechanism of miR-122 expression regulation by HCV infection . Here , we show that the HCV core protein downregulates the abundance of miR-122 by promoting its destabilization via the inhibition of GLD-2 , a non-canonical cytoplasmic poly ( A ) polymerase . The decrease in miR-122 expression resulted in the dysregulation of the known functions of miR-122 , including its proviral activity for HCV . By high-throughput sequencing of small RNAs from human liver biopsies , we found that the 22-nucleotide ( nt ) prototype miR-122 is modified at its 3 0 end by 3 0 - terminal non-templated and templated nucleotide additions . Remarkably , the proportion of miR-122 isomers bearing a single nucleotide tail of any ribonucleotide decreased in liver specimens from patients with HCV . We found that these single-nucleotide-tailed miR-122 isomers display increased miRNA activity and stability over the 22-nt prototype miR-122 and that the 3 0 - terminal extension is catalyzed by the unique terminal nucleotidyl transferase activity of GLD-2 , which is capable of adding any single ribonucleotide without preference of adenylate to the miR-122 3 0 end . The HCV core protein specifically inhibited GLD-2 , and its interaction with GLD-2 in the cytoplasm was found to be responsible for miR-122 downregulation . Collectively , our results provide new insights into the regulatory role of the HCV core protein in controlling viral RNA abundance and miR-122 functions through miR-122 stability modulation . Viruses may benefit from altering the host cell 's normal miRNA milieu , by either lowering or increasing antiviral or proviral miRNA levels . Our results reveal a mechanism by which virus infection can regulate miRNA abundance by modulating the activity of cellular enzymes responsible for miRNA 3 0 - terminal modifications . Hepatitis C virus ( HCV ) uses microRNA-122 ( miR-122 ) as a proviral host factor to increase viral genome abundance , but HCV infection results in diminished miR-122 levels by unknown mechanisms . We PLOS Pathogens | demonstrated that the HCV core protein plays a role in reprogramming the cellular profile of miR-122 isomers by inhibiting GLD-2 , a non-canonical cytoplasmic poly ( A ) polymerase , to promote miR-122 destabilization . Our results raise several important questions . First , how is only a specific subset of miRNAs in the liver affected by GLD-2 inhibition by the HCV core protein ? Second , how does HCV regulate pre-miR-122 processing in its loop region ? Third , does GLD-2 inhibition by the HCV core protein affect the translation of a specific group of host mRNAs ? With many unanswered questions , our results propose a novel feedback regulatory mechanism for controlling HCV RNA abundance by the viral capsid protein , which is capable of modulating miR-122 activity and stability through the inhibition of GLD-2 . GLD-2 Inhibition by the HCV Core Protein PLOS Pathogens |\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The liver-specific microRNA miR-122 , which has essential roles in liver development and metabolism ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"is a key proviral factor for hepatitis C virus ( HCV ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Despite its crucial role in the liver and HCV life cycle ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"little is known about the molecular mechanism of miR-122 expression regulation by HCV infection .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Here , we show that the HCV core protein downregulates the abundance of miR-122 by promoting its destabilization via the inhibition of GLD-2 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"a non-canonical cytoplasmic poly ( A ) polymerase .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"The decrease in miR-122 expression resulted in the dysregulation of the known functions of miR-122 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"including its proviral activity for HCV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"By high-throughput sequencing of small RNAs from human liver biopsies ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"we found that the 22-nucleotide ( nt ) prototype miR-122 is modified at its 3 0 end by 3 0 - terminal non-templated and templated nucleotide additions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Remarkably , the proportion of miR-122 isomers bearing a single nucleotide tail of any ribonucleotide decreased in liver specimens from patients with HCV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"We found that these single-nucleotide-tailed miR-122 isomers display increased miRNA activity and stability over the 22-nt prototype miR-122 and that the 3 0 - terminal extension is catalyzed by the unique terminal nucleotidyl transferase activity of GLD-2 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"which is capable of adding any single ribonucleotide without preference of adenylate to the miR-122 3 0 end .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"The HCV core protein specifically inhibited GLD-2 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"and its interaction with GLD-2 in the cytoplasm was found to be responsible for miR-122 downregulation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Collectively , our results provide new insights into the regulatory role of the HCV core protein in controlling viral RNA abundance and miR-122 functions through miR-122 stability modulation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Viruses may benefit from altering the host cell 's normal miRNA milieu ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"by either lowering or increasing antiviral or proviral miRNA levels .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Our results reveal a mechanism by which virus infection can regulate miRNA abundance by modulating the activity of cellular enzymes responsible for miRNA 3 0 - terminal modifications .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Hepatitis C virus ( HCV ) uses microRNA-122 ( miR-122 ) as a proviral host factor to increase viral genome abundance ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"but HCV infection results in diminished miR-122 levels by unknown mechanisms .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"We PLOS Pathogens | demonstrated that the HCV core protein plays a role in reprogramming the cellular profile of miR-122 isomers by inhibiting GLD-2 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"a non-canonical cytoplasmic poly ( A ) polymerase , to promote miR-122 destabilization .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}, {\"segment_text\": \"Our results raise several important questions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 24}, {\"segment_text\": \"First , how is only a specific subset of miRNAs in the liver affected by GLD-2 inhibition by the HCV core protein ?\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 25}, {\"segment_text\": \"Second , how does HCV regulate pre-miR-122 processing in its loop region ?\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 26}, {\"segment_text\": \"Third , does GLD-2 inhibition by the HCV core protein affect the translation of a specific group of host mRNAs ?\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 27}, {\"segment_text\": \"With many unanswered questions , our results propose a novel feedback regulatory mechanism for controlling HCV RNA abundance by the viral capsid protein ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 28}, {\"segment_text\": \"which is capable of modulating miR-122 activity and stability through the inhibition of GLD-2 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 29}, {\"segment_text\": \"GLD-2 Inhibition by the HCV Core Protein PLOS Pathogens |\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 30}]}"}]}
{"paper_id": "44f6db0cdbf4aeb5bd10e15066084b8d02e43dc8", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nNew data on bat ectoparasites from Mindoro Island , Philippines are reported . Eighty-three individuals of ectoparasitic insects representing seven species of Nycteribiidae and five species of Streblidae ( both Diptera ) , and one species of Ischnopsyllidae ( Siphonaptera ) were recorded from 11 bat species captured in Naujan Lake National Park , Mindoro Oriental Province , Philippines . Raymondia pagodarum is a new record for the country . Eight species are also newly recorded for Mindoro Island , including Cyclopodia garrula , Leptocyclopodia ferrarii mabuhai , Megastrebla parvior , Brachytarsina amboinensis , B. werneri , R. pagodarum , R. pseudopagodarum and Thaumapsylla longiforceps . Five species are newly documented on various hosts : C. horsfieldi on Pteropus pumilus , M. parvior on Macroglossus minimus , B. amboinensis on Hipposideros diadema , B. werneri on Rhinolophus arcuatus and R. pagodarum on Hipposideros bicolor .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"New data on bat ectoparasites from Mindoro Island , Philippines are reported .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Eighty-three individuals of ectoparasitic insects representing seven species of Nycteribiidae and five species of Streblidae ( both Diptera ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"and one species of Ischnopsyllidae ( Siphonaptera ) were recorded from 11 bat species captured in Naujan Lake National Park ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"Mindoro Oriental Province , Philippines .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Raymondia pagodarum is a new record for the country .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Eight species are also newly recorded for Mindoro Island ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"including Cyclopodia garrula , Leptocyclopodia ferrarii mabuhai ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Megastrebla parvior , Brachytarsina amboinensis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"B. werneri , R. pagodarum ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"R. pseudopagodarum and Thaumapsylla longiforceps .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Five species are newly documented on various hosts : C. horsfieldi on Pteropus pumilus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"M. parvior on Macroglossus minimus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"B. amboinensis on Hipposideros diadema ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"B. werneri on Rhinolophus arcuatus and R. pagodarum on Hipposideros bicolor .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "294f15aa90f5c0cbc408c1e8a9d266a7d2a1c786", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nExtensive studies suggest that although changes in immunity with healthy aging ( termed immunosenescence ) occur at the most rapid rate of any physiologic system , it is the compounding effects of age-related diseases and external conditions that result in an overall state of a dysfunctional immunity responsible for the increased risk for and severity of common infections in older adults . Hence , immunosenescence is a predisposing condition , but its contribution to infection risk likely is small until immunity is impaired further as a result of accumulating chronic illness , external conditions , or repeated or chronic infections . This is different from the changes related to immunosuppression that result from certain conditions , such as HIV infection , or immunosuppressive medications that result in unusual , opportunistic infections . Unfortunately , the challenge of studying a diverse population with multiple confounders and the focus of gerontologists on studying normal aging have limited research and understanding of why frail , older adults are so susceptible to common infections and outbreaks of infectious syndromes , including influenza , West Nile virus , and severe acute respiratory syndrome ( SARS ) and experience frequent vaccine nonresponse . The high risk for infection in those of advanced age and who have multiple comorbidities is underscored by the high rates of health care-acquired infections in older adults residing in long-term care facilities ( LTCF ) . In\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Extensive studies suggest that although changes in immunity with healthy aging ( termed immunosenescence ) occur at the most rapid rate of any physiologic system ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"it is the compounding effects of age-related diseases and external conditions that result in an overall state of a dysfunctional immunity responsible for the increased risk for and severity of common infections in older adults .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Hence , immunosenescence is a predisposing condition ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"but its contribution to infection risk likely is small until immunity is impaired further as a result of accumulating chronic illness ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"external conditions , or repeated or chronic infections .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"This is different from the changes related to immunosuppression that result from certain conditions ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"such as HIV infection , or immunosuppressive medications that result in unusual , opportunistic infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Unfortunately , the challenge of studying a diverse population with multiple confounders and the focus of gerontologists on studying normal aging have limited research and understanding of why frail ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"older adults are so susceptible to common infections and outbreaks of infectious syndromes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"including influenza , West Nile virus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"and severe acute respiratory syndrome ( SARS ) and experience frequent vaccine nonresponse .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"The high risk for infection in those of advanced age and who have multiple comorbidities is underscored by the high rates of health care-acquired infections in older adults residing in long-term care facilities ( LTCF ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"In\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 13}]}"}]}
{"paper_id": "82fb52d462dc847ed33ec87be35bd5c5065844aa", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAvian infl uenza virus ( H5N1 ) can be transmitted to humans , resulting in a severe or fatal disease . The aim of this study was to evaluate the immune cross-reactivity between human and avian infl uenza ( H5N1 ) strains in healthy donors vaccinated for seasonal infl uenza A ( H1N1 ) / ( H3N2 ) . A small frequency of CD4 T cells specifi c for subtype H5N1 was detected in several persons at baseline , and seasonal vaccine administration enhanced the frequency of such reactive CD4 T cells . We also observed that seasonal vaccination is able to raise neutralizing immunity against infl uenza ( H5N1 ) in a large number of donors . No correlation between infl uenzaspecifi c CD4 T cells and humoral responses was observed . N1 may possibly be a target for both cellular and humoral cross-type immunity , but additional experiments are needed to clarify this point . These fi ndings highlight the possibility of boosting cross-type cellular and humoral immunity against highly pathogenic avian infl uenza A virus subtype H5N1 by seasonal infl uenza vaccination .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Avian infl uenza virus ( H5N1 ) can be transmitted to humans ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"resulting in a severe or fatal disease .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The aim of this study was to evaluate the immune cross-reactivity between human and avian infl uenza ( H5N1 ) strains in healthy donors vaccinated for seasonal infl uenza A ( H1N1 ) / ( H3N2 ) .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"A small frequency of CD4 T cells specifi c for subtype H5N1 was detected in several persons at baseline ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"and seasonal vaccine administration enhanced the frequency of such reactive CD4 T cells .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"We also observed that seasonal vaccination is able to raise neutralizing immunity against infl uenza ( H5N1 ) in a large number of donors .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"No correlation between infl uenzaspecifi c CD4 T cells and humoral responses was observed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"N1 may possibly be a target for both cellular and humoral cross-type immunity ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"but additional experiments are needed to clarify this point .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"These fi ndings highlight the possibility of boosting cross-type cellular and humoral immunity against highly pathogenic avian infl uenza A virus subtype H5N1 by seasonal infl uenza vaccination .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}]}"}]}
{"paper_id": "78129f8a257ba6c3503c5ec09ab40d41a1363f6a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nOnly a month after the outbreak of pneumonia caused by 2019-nCoV , more than forty-thousand people were infected . This put enormous pressure on the Chinese government , medical healthcare provider , and the general public , but also made the international community deeply nervous . On the 25th day after the outbreak , the Chinese government implemented strict traffic restrictions on the area where the 2019-nCoV had originateddHubei province , whose capital city is Wuhan . Ten days later , the rate of increase of cases in Hubei showed a significant difference ( p 1/4 0.0001 ) compared with the total rate of increase in other provinces of China . These preliminary data suggest the effectiveness of a traffic restriction policy for this pandemic thus far . At the same time , solid financial support and improved research ability , along with network communication technology , also greatly facilitated the application of epidemic prevention measures . These measures were motivated by the need to provide effective treatment of patients , and involved consultation with three major groups in policy formulationdpublic health experts , the government , and the general public . It was also aided by media and information technology , as well as international cooperation . This experience will provide China and other countries with valuable lessons for quickly coordinating and coping with future public health emergencies .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Only a month after the outbreak of pneumonia caused by 2019-nCoV ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"more than forty-thousand people were infected .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"This put enormous pressure on the Chinese government ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"medical healthcare provider , and the general public ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"but also made the international community deeply nervous .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"On the 25th day after the outbreak ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"the Chinese government implemented strict traffic restrictions on the area where the 2019-nCoV had originateddHubei province ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"whose capital city is Wuhan .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"Ten days later , the rate of increase of cases in Hubei showed a significant difference ( p 1/4 0.0001 ) compared with the total rate of increase in other provinces of China .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"These preliminary data suggest the effectiveness of a traffic restriction policy for this pandemic thus far .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"At the same time , solid financial support and improved research ability ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"along with network communication technology ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"also greatly facilitated the application of epidemic prevention measures .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"These measures were motivated by the need to provide effective treatment of patients ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"and involved consultation with three major groups in policy formulationdpublic health experts ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"the government , and the general public .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"It was also aided by media and information technology ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"as well as international cooperation .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"This experience will provide China and other countries with valuable lessons for quickly coordinating and coping with future public health emergencies .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}]}"}]}
{"paper_id": "f558e3046f1472abb3df752a61adc9215467718f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe ssRNA + family Coronaviridae includes two subfamilies prototyped by coronaviruses and toroviruses that cause respiratory and enteric infections . To facilitate the identification of new distantly related members of the family Coronaviridae , we have developed a molecular assay with broad specificity . The consensus-degenerated hybrid oligonucleotide primer ( CODEHOP ) strategy was modified to design primers targeting the most conserved motifs in the RNA-dependent RNA polymerase locus . They were evaluated initially on RNA templates from virus-infected cells using a two-step RT-PCR protocol that was further advanced to a one-step assay . The sensitivity of the assay ranged from 10 2 to 10 6 and from 10 5 to 10 9 RNA copy numbers for individual corona - / torovirus templates when tested , respectively , with and without an excess of RNA from human cells . This primer set compared to that designed according to the original CODEHOP rules showed 10-10 3 folds greater sensitivity for 5 of the 6 evaluated corona - / torovirus templates . It detected 57 % ( 32 of 56 ) of the respiratory specimens positive for 4 human coronaviruses , as well as stool specimens positive for a bovine torovirus . The high sensitivity and broad virus range of this assay makes it suitable for screening biological specimens in search for new viruses of the family Coronaviridae .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The ssRNA + family Coronaviridae includes two subfamilies prototyped by coronaviruses and toroviruses that cause respiratory and enteric infections .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"To facilitate the identification of new distantly related members of the family Coronaviridae ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"we have developed a molecular assay with broad specificity .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"The consensus-degenerated hybrid oligonucleotide primer ( CODEHOP ) strategy was modified to design primers targeting the most conserved motifs in the RNA-dependent RNA polymerase locus .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"They were evaluated initially on RNA templates from virus-infected cells using a two-step RT-PCR protocol that was further advanced to a one-step assay .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"The sensitivity of the assay ranged from 10 2 to 10 6 and from 10 5 to 10 9 RNA copy numbers for individual corona - / torovirus templates when tested ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"respectively , with and without an excess of RNA from human cells .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"This primer set compared to that designed according to the original CODEHOP rules showed 10-10 3 folds greater sensitivity for 5 of the 6 evaluated corona - / torovirus templates .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"It detected 57 % ( 32 of 56 ) of the respiratory specimens positive for 4 human coronaviruses ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"as well as stool specimens positive for a bovine torovirus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The high sensitivity and broad virus range of this assay makes it suitable for screening biological specimens in search for new viruses of the family Coronaviridae .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}]}"}]}
{"paper_id": "2affbefeaceb705ec59074839cbe8c30413864ea", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRecent international epidemics of coronavirus-associated illnesses underscore the urgent medical and public health need for vaccine development and regulatory body approved therapies . In particular , the current coronavirus disease 2019 ( COVID-19 ) pandemic has quickly intensified interest in developing treatment options to mitigate impact on human life . Remdesivir ( GS-5734 ™ ) is a broad-spectrum antiviral drug that is now being tested as a potential treatment for COVID-19 in international , multi-site clinical trials . Currently available evidence about the antiviral effects of remdesivir against coronaviruses is primarily based on in vitro and in vivo studies ( including some on a chemically related compound , GS-441524 ™ ) , which have demonstrated largely favorable findings . As the pandemic progresses , information from human compassionate use cases will continue to accumulate before the clinical trials are concluded . It is imperative for public health practitioners and the One Health community to stay up to date on the most promising potential therapeutic options that are under investigation . Thus , the purpose of this review is to synthesize the knowledge to date about remdesivir as a therapeutic option for coronaviruses , with a special focus on information relevant to the One Health community .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Recent international epidemics of coronavirus-associated illnesses underscore the urgent medical and public health need for vaccine development and regulatory body approved therapies .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"In particular , the current coronavirus disease 2019 ( COVID-19 ) pandemic has quickly intensified interest in developing treatment options to mitigate impact on human life .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Remdesivir ( GS-5734 ™ ) is a broad-spectrum antiviral drug that is now being tested as a potential treatment for COVID-19 in international , multi-site clinical trials .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Currently available evidence about the antiviral effects of remdesivir against coronaviruses is primarily based on in vitro and in vivo studies ( including some on a chemically related compound , GS-441524 ™ ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"which have demonstrated largely favorable findings .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"As the pandemic progresses , information from human compassionate use cases will continue to accumulate before the clinical trials are concluded .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"It is imperative for public health practitioners and the One Health community to stay up to date on the most promising potential therapeutic options that are under investigation .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Thus , the purpose of this review is to synthesize the knowledge to date about remdesivir as a therapeutic option for coronaviruses ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"with a special focus on information relevant to the One Health community .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}]}"}]}
{"paper_id": "3d79f3b3c829121de0ebfcb8ff32bcbd9f4aa22d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSource : CDC ( 1998 ) Impact of vaccines universally recommended for children - US , 1990-98 . MMWR 48 : 577-581 ; modified ) ( 94 ) .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Source : CDC ( 1998 ) Impact of vaccines universally recommended for children - US , 1990-98 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 1}, {\"segment_text\": \"MMWR 48 : 577-581 ; modified ) ( 94 ) .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 2}]}"}]}
{"paper_id": "c16e9315546d0d93c95be1c6df694eda2f6da965", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nStone , S. S. , Kemeny , L. J. and Jensen , M. T. , 1982 . Serum antibody responses of neonatal and young adult pigs to transmissible gastroenteritls coronavlrus . Vet . Immunol . Immunopathol. , 3 : 529-533 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Stone , S. S. , Kemeny ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 1}, {\"segment_text\": \"L. J. and Jensen , M. T. , 1982 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 2}, {\"segment_text\": \"Serum antibody responses of neonatal and young adult pigs to transmissible gastroenteritls coronavlrus .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Vet .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 4}, {\"segment_text\": \"Immunol .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 5}, {\"segment_text\": \"Immunopathol. , 3 : 529-533 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 6}]}"}]}
{"paper_id": "9491f89b53c527904943035f8b4a1f997c3609ad", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Altered plasma concentrations of vitamin D and mannose binding lectin ( MBL ) , components of innate immunity , have been shown to be associated with the pathogenesis of viral infections . The objective of the present study was to find out whether plasma concentrations of MBL and vitamin D are different in patients with dengue fever ( DF ) and dengue hemorrhagic fever ( DHF ) . The results : The plasma concentrations of vitamin D and MBL were assessed in 48 DF cases , 45 DHF cases and 20 apparently healthy controls using ELISA based methods . Vitamin D concentrations were found to be higher among both DF and DHF cases as compared to healthy controls ( P < 0.005 and P < 0.001 ) . Vitamin D concentrations were not different between DF and DHF cases . When the dengue cases were classified into primary and secondary infections , secondary DHF cases had significantly higher concentrations of vitamin D as compared to secondary DF cases ( P < 0.050 ) . MBL concentrations were not significantly different between healthy controls and dengue cases . MBL concentrations were observed to be lower in DHF cases as compared to DF cases ( P < 0.050 ) . Although MBL levels were not different DF and DHF cases based on immune status , the percentage of primary DHF cases ( 50 % ) having MBL levels lower than 500 ng/ml were less compared to primary DF cases ( P = 0.038 ) . Conclusions : The present study suggests that higher concentrations of vitamin D might be associated with secondary DHF while deficiency of MBL may be associated with primary DHF .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Altered plasma concentrations of vitamin D and mannose binding lectin ( MBL ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"components of innate immunity , have been shown to be associated with the pathogenesis of viral infections .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"The objective of the present study was to find out whether plasma concentrations of MBL and vitamin D are different in patients with dengue fever ( DF ) and dengue hemorrhagic fever ( DHF ) .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"The results : The plasma concentrations of vitamin D and MBL were assessed in 48 DF cases ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"45 DHF cases and 20 apparently healthy controls using ELISA based methods .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Vitamin D concentrations were found to be higher among both DF and DHF cases as compared to healthy controls ( P < 0.005 and P < 0.001 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"Vitamin D concentrations were not different between DF and DHF cases .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"When the dengue cases were classified into primary and secondary infections ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"secondary DHF cases had significantly higher concentrations of vitamin D as compared to secondary DF cases ( P < 0.050 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"MBL concentrations were not significantly different between healthy controls and dengue cases .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"MBL concentrations were observed to be lower in DHF cases as compared to DF cases ( P < 0.050 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"Although MBL levels were not different DF and DHF cases based on immune status ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"the percentage of primary DHF cases ( 50 % ) having MBL levels lower than 500 ng/ml were less compared to primary DF cases ( P = 0.038 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"Conclusions : The present study suggests that higher concentrations of vitamin D might be associated with secondary DHF while deficiency of MBL may be associated with primary DHF .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "86d626bc8e5985b1114bc4b6c21b4b8f1b45a64a", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nToroviruses are emergent viruses , belonging to the Nidovirales order , that remain mostly ignored , despite they are able to infect different species of domestic animals and humans , causing enteric diseases and diarrhea . Thus far , only five variants of porcine torovirus ( PToV ) have been identified . In this report we describe the identification and partial characterization of a new strain of porcine torovirus ( PToV-BRES ) that was detected by RT-PCR in a swine faecal specimen from a farm in Brescia ( Italy ) . The complete genes coding for the nucleocapsid ( N ) , hemagglutinin-esterase ( HE ) and membrane ( M ) proteins were amplified , and sequence analysis showed that PToV-BRES is a new PToV strain that , based on the HE gene sequence , is phylogenetically related to P4 strain , that was up to now the only member of a distinct PToV lineage . The nucleocapsid protein from PToV-BRES was expressed in insect cells as a his-tagged protein , purified by affinity chromatography and used to develop an ELISA method to detect antibodies against PToV . This assay was evaluated using a serum collection including 45 samples from three commercial farms from Spain . High antibody prevalence against PToV was observed in the three farms , both in adult animals and in piglets , which could suggest that PToV might be endemic in Spanish porcine population . The ELISA method developed in this work could be useful in future epidemiological surveys about toroviruses .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Toroviruses are emergent viruses , belonging to the Nidovirales order ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"that remain mostly ignored , despite they are able to infect different species of domestic animals and humans ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"causing enteric diseases and diarrhea .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Thus far , only five variants of porcine torovirus ( PToV ) have been identified .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"In this report we describe the identification and partial characterization of a new strain of porcine torovirus ( PToV-BRES ) that was detected by RT-PCR in a swine faecal specimen from a farm in Brescia ( Italy ) .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"The complete genes coding for the nucleocapsid ( N ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"hemagglutinin-esterase ( HE ) and membrane ( M ) proteins were amplified ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"and sequence analysis showed that PToV-BRES is a new PToV strain that ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"based on the HE gene sequence ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 9}, {\"segment_text\": \"is phylogenetically related to P4 strain ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 10}, {\"segment_text\": \"that was up to now the only member of a distinct PToV lineage .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 11}, {\"segment_text\": \"The nucleocapsid protein from PToV-BRES was expressed in insect cells as a his-tagged protein ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"purified by affinity chromatography and used to develop an ELISA method to detect antibodies against PToV .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"This assay was evaluated using a serum collection including 45 samples from three commercial farms from Spain .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"High antibody prevalence against PToV was observed in the three farms ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"both in adult animals and in piglets ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"which could suggest that PToV might be endemic in Spanish porcine population .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"The ELISA method developed in this work could be useful in future epidemiological surveys about toroviruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "22faab96b423cab9df3cd453727e6a7763de4bb6", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe aim of the study was assessment of the usefulness of multiplex real-time PCR tests in the diagnostic and therapeutic process in children hospitalized due to pneumonia and burdened with comorbidities . Methods . The study group included 97 children hospitalized due to pneumonia at the Karol Jonscher Teaching Hospital in Poznań , in whom multiplex real-time PCR tests ( FTD respiratory pathogens 33 ; fast-track diagnostics ) were used . Results . Positive test results of the test were achieved in 74 patients ( 76.3 % ) . The average age in the group was 56 months . Viruses were detected in 61 samples ( 82 % of all positive results ) ; bacterial factors were found in 29 samples ( 39 % of all positive results ) . The presence of comorbidities was established in 90 children ( 92.78 % ) . On the basis of the obtained results , 5 groups of patients were established : viral etiology of infection , 34 patients ; bacterial etiology , 7 patients ; mixed etiology , 23 patients ; pneumocystis , 9 patients ; and no etiology diagnosed , 24 patients . Conclusions . Our analysis demonstrated that the participation of viruses in causing severe lung infections is significant in children with comorbidities . Multiplex real-time PCR tests proved to be more useful in establishing the etiology of pneumonia in hospitalized children than the traditional microbiological examinations .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The aim of the study was assessment of the usefulness of multiplex real-time PCR tests in the diagnostic and therapeutic process in children hospitalized due to pneumonia and burdened with comorbidities .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Methods .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"The study group included 97 children hospitalized due to pneumonia at the Karol Jonscher Teaching Hospital in Poznań ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"in whom multiplex real-time PCR tests ( FTD respiratory pathogens 33 ; fast-track diagnostics ) were used .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Results .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"Positive test results of the test were achieved in 74 patients ( 76.3 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"The average age in the group was 56 months .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Viruses were detected in 61 samples ( 82 % of all positive results ) ; bacterial factors were found in 29 samples ( 39 % of all positive results ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"The presence of comorbidities was established in 90 children ( 92.78 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"On the basis of the obtained results ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"5 groups of patients were established : viral etiology of infection ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"34 patients ; bacterial etiology ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"7 patients ; mixed etiology ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"23 patients ; pneumocystis , 9 patients ; and no etiology diagnosed , 24 patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Conclusions .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"Our analysis demonstrated that the participation of viruses in causing severe lung infections is significant in children with comorbidities .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Multiplex real-time PCR tests proved to be more useful in establishing the etiology of pneumonia in hospitalized children than the traditional microbiological examinations .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "31a96328b07bd673d42058a8871b15a287cd937c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSanekata , T. , Kishimoto , E. , Sato , K. , Honma , H. , Otsuki , K. and Tsubokura , M. , 1991 . Detection of poricine rotavirus in stools by a latex agglutination test . Vet . Microbiol. , 27:245-251 . We developed a simple agglutination test for the detection of porcine rotavirus in stools from pigs with diarrhea . The virus was detected with high sensitivity and specificity by a slide agglutination test using latex particles coated with antibody against the porcine rotavirus strain OSU ( LA-antiOSU ) . The agglutination of LA-antiOSU with OSU on a glass slide was evident macroscopically within 2 rain . The sensitivity of this latex agglutination ( LA ) test was four times higher than that of the electron microscope method . The LA test is available for the rapid diagnosis of porcine rotavirus infections .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Sanekata , T. , Kishimoto ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 1}, {\"segment_text\": \"E. , Sato , K. ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 2}, {\"segment_text\": \"Honma , H. , Otsuki ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 3}, {\"segment_text\": \"K. and Tsubokura , M. , 1991 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 4}, {\"segment_text\": \"Detection of poricine rotavirus in stools by a latex agglutination test .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 5}, {\"segment_text\": \"Vet .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 6}, {\"segment_text\": \"Microbiol. , 27:245-251 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 7}, {\"segment_text\": \"We developed a simple agglutination test for the detection of porcine rotavirus in stools from pigs with diarrhea .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"The virus was detected with high sensitivity and specificity by a slide agglutination test using latex particles coated with antibody against the porcine rotavirus strain OSU ( LA-antiOSU ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"The agglutination of LA-antiOSU with OSU on a glass slide was evident macroscopically within 2 rain .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The sensitivity of this latex agglutination ( LA ) test was four times higher than that of the electron microscope method .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"The LA test is available for the rapid diagnosis of porcine rotavirus infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "5ef09ce2073f1063d9c5877c8ba89955075b463e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nDuring th e pas t thre e decades , ther e ha s bee n a growin g realizatio n tha t breast-feeding no t only provides the nutritional requirements of the infant , but als o supplie s a hos t o f defens e factor s fo r th e protectio n o f th e recipient and/o r th e mammar y gland . Th e stud y o f thi s remarkabl e defense syste m in huma n mil k ha s bee n difficult , however , becaus e o f it s biochemical complexities , th e smal l concentration s o f certai n ver y poten t agents i n huma n milk , th e nee d t o develo p specia l method s t o quantif y certain factor s becaus e o f thei r particula r form s i n huma n milk , th e compartmentalization o f some of the agents , and the dynamic effects o f th e length o f lactatio n an d othe r materna l factor s upo n th e concentration s o r functions o f th e component s o f th e system . I n thi s chapter , w e summariz e the current information concernin g the molecular forms , concentrations i n milk durin g th e severa l phase s o f lactation , biologica l activities , fat e i n th e recipient infant , an d in vivo functions o f the defense agent s in human milk . ( 2 ) mos t component s of th e immunologi c syste m i n huma n mil k ar e produce d throughou t lactation an d durin g gradua l weaning ; ( 3 ) th e factor s ar e usuall y commo n to othe r mucosa l sites ; ( 4 ) the y ar e adapte d t o resis t digestio n i n th e gastrointestinal trac t of th e recipien t infant ; ( 5 ) they protec t b y noninflammatory mechanisms ; an d ( 6 ) th e agent s ac t synergisticall y wit h eac h othe r or with defense agent s produced b y the recipient . Representativ e example s of solubl e defens e agent s ar e liste d i n Tabl e I .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"During th e pas t thre e decades ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"ther e ha s bee n a growin g realizatio n tha t breast-feeding no t only provides the nutritional requirements of the infant ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"but als o supplie s a hos t o f defens e factor s fo r th e protectio n o f th e recipient and/o r th e mammar y gland .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Th e stud y o f thi s remarkabl e defense syste m in huma n mil k ha s bee n difficult ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"however , becaus e o f it s biochemical complexities ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"th e smal l concentration s o f certai n ver y poten t agents i n huma n milk ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"th e nee d t o develo p specia l method s t o quantif y certain factor s becaus e o f thei r particula r form s i n huma n milk ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"th e compartmentalization o f some of the agents ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"and the dynamic effects o f th e length o f lactatio n an d othe r materna l factor s upo n th e concentration s o r functions o f th e component s o f th e system .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"I n thi s chapter ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 10}, {\"segment_text\": \"w e summariz e the current information concernin g the molecular forms ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 11}, {\"segment_text\": \"concentrations i n milk durin g th e severa l phase s o f lactation ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}, {\"segment_text\": \"biologica l activities , fat e i n th e recipient infant ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 13}, {\"segment_text\": \"an d in vivo functions o f the defense agent s in human milk .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 14}, {\"segment_text\": \"( 2 ) mos t component s of th e immunologi c syste m i n huma n mil k ar e produce d throughou t lactation an d durin g gradua l weaning ; ( 3 ) th e factor s ar e usuall y commo n to othe r mucosa l sites ; ( 4 ) the y ar e adapte d t o resis t digestio n i n th e gastrointestinal trac t of th e recipien t infant ; ( 5 ) they protec t b y noninflammatory mechanisms ; an d ( 6 ) th e agent s ac t synergisticall y wit h eac h othe r or with defense agent s produced b y the recipient .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Representativ e example s of solubl e defens e agent s ar e liste d i n Tabl e I .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "821adc5f0139622999cf4d6a2f622b51b15a07bc", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nNewcastle disease virus ( NDV ) causes morbidities and mortalities in wild and domestic birds globally . For humans , exposure to infected birds can cause conjunctivitis and influenza-like symptoms . NDV infections in mammals are rarely reported . In this study , using next-generation sequencing , an NDV was identified and isolated from Vero cells inoculated with the nasal swab of an aborted dromedary fetus in Dubai , during the time when an NDV outbreak occurred in a pigeon farm located in close proximity to the dairy camel farm where the mother of the aborted dromedary fetus resided , and there were a lot of pigeons in the camel farm . Genome analysis revealed that the structurally and functionally important features of other NDVs were also present in this dromedary NDV genome . Phylogenetic analysis based on the nucleotide sequences of fusion protein ( F ) , hemagglutinin-neuraminidase protein ( HN ) and complete polyprotein showed that the virus belonged to sub-genotype VIg of class II NDV and is most closely related to pigeon NDVs in Egypt in the same year . The present study is the first that demonstrated isolation of NDV in dromedaries . Further study is warranted to investigate the relationship between NDV infection and abortion .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Newcastle disease virus ( NDV ) causes morbidities and mortalities in wild and domestic birds globally .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"For humans , exposure to infected birds can cause conjunctivitis and influenza-like symptoms .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"NDV infections in mammals are rarely reported .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"In this study , using next-generation sequencing ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"an NDV was identified and isolated from Vero cells inoculated with the nasal swab of an aborted dromedary fetus in Dubai ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"during the time when an NDV outbreak occurred in a pigeon farm located in close proximity to the dairy camel farm where the mother of the aborted dromedary fetus resided ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"and there were a lot of pigeons in the camel farm .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Genome analysis revealed that the structurally and functionally important features of other NDVs were also present in this dromedary NDV genome .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Phylogenetic analysis based on the nucleotide sequences of fusion protein ( F ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"hemagglutinin-neuraminidase protein ( HN ) and complete polyprotein showed that the virus belonged to sub-genotype VIg of class II NDV and is most closely related to pigeon NDVs in Egypt in the same year .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The present study is the first that demonstrated isolation of NDV in dromedaries .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Further study is warranted to investigate the relationship between NDV infection and abortion .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "9c016d8d0a0e01eaa2f449c5c779a6ecce82ff17", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nLimited data exist on how SARS-CoV-2 enters and spreads in the general population . We used two strategies for SARS-CoV-2 testing : targeted testing of high-risk individuals ( n = 4,551 ) and a population screening ( n = 5,502 ) . We sequenced SARS-CoV-2 from 340 individuals . RESULTS March 22 2020 , 528 had tested positive for SARS-CoV-2 in the targeted testing ( 11.6 % ) and 50 in the population screening ( 0.9 % ) ; approximately 0.2 % of the Icelandic population . Large fractions of positives had travelled outside Iceland ( 38.4 % and 34.0 % ) . Fewer under 10 years old were positive than those older : 2.8 % vs. 12.3 % for targeted testing ( P = 1.6e-9 ) and 0.0 % vs. 1.0 % for population screening ( P = 0.031 ) . Fewer females were positive in the targeted testing than males ( 9.5 % vs. 14.6 % , P = 6.8e-9 ) . SARS-CoV-2 came from eight clades , seven A clades and one B clade . The clade composition differed between the testing groups and changed with time . In the early targeted testing , 65.0 % of clades were A2a1 and A2a2 derived from Italian and Austrian skiing areas , but in the later targeted testing went down to 30.6 % and were overtaken by A1a and A2a , the most common clades in the population screening . SARS-CoV-2 has spread widely in Iceland outside of the high-risk groups . Several strains cause these infections and their relative contribution changed rapidly .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Limited data exist on how SARS-CoV-2 enters and spreads in the general population .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"We used two strategies for SARS-CoV-2 testing : targeted testing of high-risk individuals ( n = 4,551 ) and a population screening ( n = 5,502 ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"We sequenced SARS-CoV-2 from 340 individuals .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"RESULTS\", \"label\": \"finding\", \"decision_reference\": \"other.definition\", \"id\": 4}, {\"segment_text\": \"March 22 2020 , 528 had tested positive for SARS-CoV-2 in the targeted testing ( 11.6 % ) and 50 in the population screening ( 0.9 % ) ; approximately 0.2 % of the Icelandic population .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"Large fractions of positives had travelled outside Iceland ( 38.4 % and 34.0 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"Fewer under 10 years old were positive than those older : 2.8 % vs. 12.3 %\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"for targeted testing ( P = 1.6e-9 ) and 0.0 % vs. 1.0 % for population screening ( P = 0.031 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"Fewer females were positive in the targeted testing than males ( 9.5 % vs. 14.6 % , P = 6.8e-9 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"SARS-CoV-2 came from eight clades ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"seven A clades and one B clade .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"The clade composition differed between the testing groups and changed with time .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"In the early targeted testing ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"65.0 % of clades were A2a1 and A2a2 derived from Italian and Austrian skiing areas ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"but in the later targeted testing went down to 30.6 % and were overtaken by A1a and A2a ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"the most common clades in the population screening .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"SARS-CoV-2 has spread widely in Iceland outside of the high-risk groups .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"Several strains cause these infections and their relative contribution changed rapidly .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}]}"}]}
{"paper_id": "b3c48ec62449227c57b0e8d71b990f2ed56277aa", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThis report describes a clinical case of feline infectious peritonitis ( FIP ) with multisystemic involvement , including multiple nodular cutaneous lesions , in a cat that was co-infected with feline coronavirus and feline immunodeficiency virus . The skin lesions were caused by a pyogranulomatous-necrotising dermal phlebitis and periphlebitis . Immunohistology demonstrated the presence of coronavirus antigen in macrophages within these lesions . The pathogenesis of FIP involves a viral associated , disseminated phlebitis and periphlebitis which can arise at many sites . Target organs frequently include the eyes , abdominal organs , pleural and peritoneal membranes , and central nervous tissues , but cutaneous lesions have not previously been reported .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"This report describes a clinical case of feline infectious peritonitis ( FIP ) with multisystemic involvement ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"including multiple nodular cutaneous lesions ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"in a cat that was co-infected with feline coronavirus and feline immunodeficiency virus .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"The skin lesions were caused by a pyogranulomatous-necrotising dermal phlebitis and periphlebitis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Immunohistology demonstrated the presence of coronavirus antigen in macrophages within these lesions .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"The pathogenesis of FIP involves a viral associated ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"disseminated phlebitis and periphlebitis which can arise at many sites .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Target organs frequently include the eyes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"abdominal organs , pleural and peritoneal membranes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"and central nervous tissues , but cutaneous lesions have not previously been reported .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "d148b4605ee294b7ec85f667a07768f1d5a1580d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nWe demonstrated a lateral flow immunoassay ( LFA ) for detection of viruses using fluorescentlylabeled M13 bacteriophage as reporters and single-reporter counting as the readout . AviTagbiotinylated M13 phage were functionalized with antibodies using avidin-biotin conjugation and fluorescently labeled with AlexaFluor 555 . Individual phage bound to target viruses ( here MS2 as a model ) captured on an LFA membrane strip were imaged using epi-fluorescence microscopy . Using automated image processing , we counted the number of bound phage in micrographs as a function of target concentration . The resultant assay was more sensitive than enzyme-linked immunosorbent assays and traditional colloidal-gold nanoparticle LFAs for direct detection of viruses . . Supporting Information : Supporting Methods , including a description of the HABA assay , measurement of the degree of biotinylation , and an automated particle-counting program for magnetic beads ; Supporting Results , including magnetic bead assay , evaluation of antibody attachment to Fusion 5 membranes , t-test comparison for phage assay , and replicate of phage assay . This information is available free of charge via the Internet at\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"We demonstrated a lateral flow immunoassay ( LFA ) for detection of viruses using fluorescentlylabeled M13 bacteriophage as reporters and single-reporter counting as the readout .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 1}, {\"segment_text\": \"AviTagbiotinylated M13 phage were functionalized with antibodies using avidin-biotin conjugation and fluorescently labeled with AlexaFluor 555 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"Individual phage bound to target viruses ( here MS2 as a model ) captured on an LFA membrane strip were imaged using epi-fluorescence microscopy .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Using automated image processing , we counted the number of bound phage in micrographs as a function of target concentration .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"The resultant assay was more sensitive than enzyme-linked immunosorbent assays and traditional colloidal-gold nanoparticle LFAs for direct detection of viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \".\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 6}, {\"segment_text\": \"Supporting Information : Supporting Methods ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 7}, {\"segment_text\": \"including a description of the HABA assay ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"measurement of the degree of biotinylation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"and an automated particle-counting program for magnetic beads ; Supporting Results ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"including magnetic bead assay , evaluation of antibody attachment to Fusion 5 membranes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"t-test comparison for phage assay ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"and replicate of phage assay .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"This information is available free of charge via the Internet at\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 14}]}"}]}
{"paper_id": "8b66b1e98d4b1e163803e87aff34f6917d16dc36", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBats are the natural reservoirs of severe acute respiratory syndrome coronavirus ( SARS-CoV ) which caused the outbreak of human SARS in 2002-2003 . We introduce the genetic diversity of SARS-related coronaviruses ( SARSr-CoVs ) discovered in bats and provide insights on the bat origin of human SARS . We also analyze the viral geographical structure that may improve our understanding of the evolution of bat SARSr-CoVs .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Bats are the natural reservoirs of severe acute respiratory syndrome coronavirus ( SARS-CoV ) which caused the outbreak of human SARS in 2002-2003 .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"We introduce the genetic diversity of SARS-related coronaviruses ( SARSr-CoVs ) discovered in bats and provide insights on the bat origin of human SARS .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"We also analyze the viral geographical structure that may improve our understanding of the evolution of bat SARSr-CoVs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}]}"}]}
{"paper_id": "7089e8b9423d428a8e1539366978157492f89f19", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe Dengue virus ( DENV ) genome contains multiple cis-acting elements required for translation and replication . Previous studies indicated that a 719-nt subgenomic minigenome ( DENV-MINI ) is an efficient template for translation and ( À ) strand RNA synthesis in vitro . We performed a detailed structural analysis of DENV-MINI RNA , combining chemical acylation techniques , Pb 2 + ion-induced hydrolysis and site-directed mutagenesis . Our results highlight protein-independent 5 0 -3 0 terminal interactions involving hybridization between recognized cisacting motifs . Probing analyses identified tandem dumbbell structures ( DBs ) within the 3 0 terminus spaced by single-stranded regions , internal loops and hairpins with embedded GNRA-like motifs . Analysis of conserved motifs and top loops ( TLs ) of these dumbbells , and their proposed interactions with downstream pseudoknot ( PK ) regions , predicted an H-type pseudoknot involving TL1 of the 5 0 DB and the complementary region , PK2 . As disrupting the TL1/PK2 interaction , via ` flipping ' mutations of PK2 , previously attenuated DENV replication , this pseudoknot may participate in regulation of RNA synthesis . Computer modeling implied that this motif might function as autonomous structural/regulatory element . In addition , our studies targeting elements of the 3 0 DB and its complementary region PK1 indicated that communication between 5 0 -3 0 terminal regions strongly depends on structure and sequence composition of the 5 0 cyclization region .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The Dengue virus ( DENV ) genome contains multiple cis-acting elements required for translation and replication .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Previous studies indicated that a 719-nt subgenomic minigenome ( DENV-MINI ) is an efficient template for translation and ( À ) strand RNA synthesis in vitro .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"We performed a detailed structural analysis of DENV-MINI RNA ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"combining chemical acylation techniques , Pb 2 + ion-induced hydrolysis and site-directed mutagenesis .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Our results highlight protein-independent 5 0 -3 0 terminal interactions involving hybridization between recognized cisacting motifs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Probing analyses identified tandem dumbbell structures ( DBs ) within the 3 0 terminus spaced by single-stranded regions ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"internal loops and hairpins with embedded GNRA-like motifs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Analysis of conserved motifs and top loops ( TLs ) of these dumbbells ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"and their proposed interactions with downstream pseudoknot ( PK ) regions ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"predicted an H-type pseudoknot involving TL1 of the 5 0 DB and the complementary region , PK2 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"As disrupting the TL1/PK2 interaction ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"via ` flipping ' mutations of PK2 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"previously attenuated DENV replication , this pseudoknot may participate in regulation of RNA synthesis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Computer modeling implied that this motif might function as autonomous structural/regulatory element .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"In addition , our studies targeting elements of the 3 0 DB and its complementary region PK1 indicated that communication between 5 0 -3 0 terminal regions strongly depends on structure and sequence composition of the 5 0 cyclization region .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}]}"}]}
{"paper_id": "d6a98a653f12caba3f539f01b0fd84b2ca4f1672", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nActivation of autoreactive T cells is a necessary-but not sufficient-step in the development of T cell mediated autoimmunity . Autoreactive T cells can be activated by viral and bacterial peptides that meet the structural requirements for MHC molecule binding and T cell receptor recognition . Due to the degenerate nature of MHC class 11 molecule binding motifs and a certain degree of flexibility in T cell receptor recognition , such microbial peptides have been found to be quite distinct in their primary sequence from the self-peptide they mimic .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Activation of autoreactive T cells is a necessary-but not sufficient-step in the development of T cell mediated autoimmunity .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Autoreactive T cells can be activated by viral and bacterial peptides that meet the structural requirements for MHC molecule binding and T cell receptor recognition .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Due to the degenerate nature of MHC class 11 molecule binding motifs and a certain degree of flexibility in T cell receptor recognition ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"such microbial peptides have been found to be quite distinct in their primary sequence from the self-peptide they mimic .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}]}"}]}
{"paper_id": "d3f7afa8b4d0f21b23ccb1135dec12356375f5cc", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRecommended treatment of chronic hepatitis B with interferon-α and/or nucleos ( t ) ide analogues does not lead to a satisfactory result . Induction of HBV-specific T cells by therapeutic vaccination or immunotherapies may be an innovative strategy to overcome virus persistence . Vaccination with commercially available HBV vaccines in patients did not result in effective control of HBV infection , suggesting that new formulations of therapeutic vaccines are needed . The woodchuck ( Marmota monax ) is a useful preclinical model for developing the new therapeutic approaches in chronic hepadnaviral infections . Several innovative approaches combining antiviral treatments with nucleos ( t ) ide analogues , DNA vaccines , and protein vaccines were tested in the woodchuck model . In this paper we summarize the available data concerning therapeutic immunization and gene therapy using recombinant viral vectors approaches in woodchucks , which show encouraging results . In addition , we present potential innovations in immunomodulatory strategies to be evaluated in this animal model .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Recommended treatment of chronic hepatitis B with interferon-α and/or nucleos ( t ) ide analogues does not lead to a satisfactory result .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Induction of HBV-specific T cells by therapeutic vaccination or immunotherapies may be an innovative strategy to overcome virus persistence .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Vaccination with commercially available HBV vaccines in patients did not result in effective control of HBV infection ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"suggesting that new formulations of therapeutic vaccines are needed .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"The woodchuck ( Marmota monax ) is a useful preclinical model for developing the new therapeutic approaches in chronic hepadnaviral infections .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Several innovative approaches combining antiviral treatments with nucleos ( t ) ide analogues ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"DNA vaccines , and protein vaccines were tested in the woodchuck model .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"In this paper we summarize the available data concerning therapeutic immunization and gene therapy using recombinant viral vectors approaches in woodchucks , which show encouraging results .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"In addition , we present potential innovations in immunomodulatory strategies to be evaluated in this animal model .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}]}"}]}
{"paper_id": "1b86ce9136c661b5bcd18f7cd529595c0e482719", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRespiratory immunization is an attractive way to generate systemic and mucosal protective memory responses that are required for preventing mucosally transmitted infections . However , the molecular and cellular mechanisms for controlling memory T cell responses remain incompletely understood . In this study , we investigated the role of respiratory macrophage ( MU ) in regulating CD4 T cell responses to recombinant adenovirus-based ( rAd ) vaccines . We demonstrated that rAd intranasal ( i.n. ) vaccination induced migration and accumulation of respiratory MU and circulatory monocytes in the mediastinal lymph nodes and lung parenchyma . Under the influence of respiratory MU CD4 T cells exhibited slow proliferation kinetics and an increased tendency of generating central memory , as opposed to effector memory , CD4 T cell responses in vitro and in vivo . Correspondingly , depletion of MU using clodronatecontaining liposome prior to i.n. immunization significantly enhanced CD4 T cell proliferation and increased the frequency of CD4 memory T cells in the airway lumen , demonstrating that MU initially serve as a negative regulator in limiting generation of mucosal tissue-resident memory CD4 T cells . However , clodronate-containing liposome delivery following i.n. immunization markedly reduced the frequencies of memory CD4 T cells in the airway lumen and spleen , indicating that respiratory MU and potentially circulating monocytes are critically required for maintaining long-term memory CD4 T cells . Collectively , our data demonstrate that rAd-induced mucosal CD4 T memory responses are regulated by respiratory MU and/or monocytes at multiple stages .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Respiratory immunization is an attractive way to generate systemic and mucosal protective memory responses that are required for preventing mucosally transmitted infections .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"However , the molecular and cellular mechanisms for controlling memory T cell responses remain incompletely understood .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"In this study , we investigated the role of respiratory macrophage ( MU ) in regulating CD4 T cell responses to recombinant adenovirus-based ( rAd ) vaccines .\", \"label\": \"background\", \"decision_reference\": \"boundary background_vs_purpose\", \"id\": 3}, {\"segment_text\": \"We demonstrated that rAd intranasal ( i.n. ) vaccination induced migration and accumulation of respiratory MU and circulatory monocytes in the mediastinal lymph nodes and lung parenchyma .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Under the influence of respiratory MU CD4 T cells exhibited slow proliferation kinetics and an increased tendency of generating central memory ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"as opposed to effector memory ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"CD4 T cell responses in vitro and in vivo .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Correspondingly , depletion of MU using clodronatecontaining liposome prior to i.n. immunization significantly enhanced CD4 T cell proliferation and increased the frequency of CD4 memory T cells in the airway lumen ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"demonstrating that MU initially serve as a negative regulator in limiting generation of mucosal tissue-resident memory CD4 T cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"However , clodronate-containing liposome delivery following i.n. immunization markedly reduced the frequencies of memory CD4 T cells in the airway lumen and spleen ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"indicating that respiratory MU and potentially circulating monocytes are critically required for maintaining long-term memory CD4 T cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Collectively , our data demonstrate that rAd-induced mucosal CD4 T memory responses are regulated by respiratory MU and/or monocytes at multiple stages .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}]}"}]}
{"paper_id": "631c92f10837ef3a7e8838f2eb19cf2f8c5d74de", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nTo comprehensively understand the endocytosis of Sapelovirus A ( PSV ) entry into PK-15 cells , we studied PSV infection in the context of cell perturbations through drug inhibition , siRNA silencing and overexpression of dominant negative ( DN ) mutants . We showed here that PSV infection of PK-15 cells was unaffected by pretreated with chlorpromazine , EIPA , knockdown of the clathrin heavy chain or overexpression of Eps15 DN mutant . Conversely , PSV infection was sensitive to NH 4 Cl , chloroquine , dynasore , nystatin , MβCD and wortmannin with reduced PSV VP1 expression levels and virus titer . Additionally , PSV invasion leaded to rapid actin rearrangement and disruption of the cellular actin network enhanced PSV infection . After internalization the virus was transported to late endosomes and/or cycling endosomes that requires the participation of Rab7 and Rab11 . Our findings demonstrate that PSV uses caveolae-dependent endocytosis as the predominant entry portal into PK-15 cells which requires low pH , dynamin , Rab7 and Rab11 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"To comprehensively understand the endocytosis of Sapelovirus A ( PSV ) entry into PK-15 cells ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"we studied PSV infection in the context of cell perturbations through drug inhibition ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"siRNA silencing and overexpression of dominant negative ( DN ) mutants .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"We showed here that PSV infection of PK-15 cells was unaffected by pretreated with chlorpromazine ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"EIPA , knockdown of the clathrin heavy chain or overexpression of Eps15 DN mutant .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Conversely , PSV infection was sensitive to NH 4 Cl ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"chloroquine , dynasore , nystatin ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"MβCD and wortmannin with reduced PSV VP1 expression levels and virus titer .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Additionally , PSV invasion leaded to rapid actin rearrangement and disruption of the cellular actin network enhanced PSV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"After internalization the virus was transported to late endosomes and/or cycling endosomes that requires the participation of Rab7 and Rab11 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Our findings demonstrate that PSV uses caveolae-dependent endocytosis as the predominant entry portal into PK-15 cells which requires low pH ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"dynamin , Rab7 and Rab11 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}]}"}]}
{"paper_id": "62e4e3bb07c0d49b928f9cfb46d2efedc04991dd", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIn ostriches , the population densities resulting from intensive rearing increases susceptibility to pathogens such as mycoplasmas . In addition to good management practices , vaccination offers an attractive alternative for controlling mycoplasma infections in food animals , instead of using antibiotics , which often leave unacceptable residues . The use of live attenuated vaccines , however , carry the concern of reversion to virulence or genetic recombination with field strains . Currently there are no commercially available vaccines against ostrich-infecting mycoplasmas and this study therefore set out to develop and evaluate the use of a DNA vaccine against mycoplasma infections in ostriches using an OppA protein as antigen . To this end , the oppA gene of `` Mycoplasma nasistruthionis sp. nov. '' str . Ms03 was cloned into two DNA vaccine expression vectors after codon correction by site-directed mutagenesis . Three-months-old ostriches were then vaccinated intramuscularly at different doses followed by a booster vaccination after 6 weeks . The ability of the DNA vaccines to elicit an anti-OppA antibody response was evaluated by ELISA using the recombinant OppA protein of Ms03 as coating antigen . A statistically significant anti-OppA antibody response could be detected after administration of a booster vaccination indicating that the OppA protein was successfully immunogenic . The responses were also both dose and vector dependent . In conclusion , the DNA vaccines were able to elicit an immune response in ostriches and can therefore be viewed as an option for the development of vaccines against mycoplasma infections .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"In ostriches , the population densities resulting from intensive rearing increases susceptibility to pathogens such as mycoplasmas .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"In addition to good management practices ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"vaccination offers an attractive alternative for controlling mycoplasma infections in food animals ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"instead of using antibiotics , which often leave unacceptable residues .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"The use of live attenuated vaccines ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"however , carry the concern of reversion to virulence or genetic recombination with field strains .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Currently there are no commercially available vaccines against ostrich-infecting mycoplasmas and this study therefore set out to develop and evaluate the use of a DNA vaccine against mycoplasma infections in ostriches using an OppA protein as antigen .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"To this end , the oppA gene of `` Mycoplasma nasistruthionis sp. nov. '' str .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Ms03 was cloned into two DNA vaccine expression vectors after codon correction by site-directed mutagenesis .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Three-months-old ostriches were then vaccinated intramuscularly at different doses followed by a booster vaccination after 6 weeks .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"The ability of the DNA vaccines to elicit an anti-OppA antibody response was evaluated by ELISA using the recombinant OppA protein of Ms03 as coating antigen .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"A statistically significant anti-OppA antibody response could be detected after administration of a booster vaccination indicating that the OppA protein was successfully immunogenic .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"The responses were also both dose and vector dependent .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"In conclusion , the DNA vaccines were able to elicit an immune response in ostriches and can therefore be viewed as an option for the development of vaccines against mycoplasma infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "a65ed49e9217467923e8db733109be6e54b0bd09", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Primary ciliary dyskinesia ( PCD ) is a rare congenital respiratory disorder characterized by abnormal ciliary motility leading to chronic airway infections . Qualitative evaluation of ciliary beat pattern based on digital high-speed videomicroscopy analysis has been proposed in the diagnosis process of PCD . Although this evaluation is easy in typical cases , it becomes difficult when ciliary beating is partially maintained . We postulated that a quantitative analysis of beat pattern would improve PCD diagnosis . We compared quantitative parameters with the qualitative evaluation of ciliary beat pattern in patients in whom the diagnosis of PCD was confirmed or excluded . Methods : Nasal nitric oxide measurement , nasal brushings and biopsies were performed prospectively in 34 patients with suspected PCD . In combination with qualitative analysis , 12 quantitative parameters of ciliary beat pattern were determined on high-speed videomicroscopy recordings of beating ciliated edges . The combination of ciliary ultrastructural abnormalities on transmission electron microscopy analysis with low nasal nitric oxide levels was the `` gold standard '' used to establish the diagnosis of PCD . Results : This `` gold standard '' excluded PCD in 15 patients ( non-PCD patients ) , confirmed PCD in 10 patients ( PCD patients ) and was inconclusive in 9 patients . Among the 12 parameters , the distance traveled by the cilium tip weighted by the percentage of beating ciliated edges presented 96 % sensitivity and 95 % specificity . Qualitative evaluation and quantitative analysis were concordant in non-PCD patients . In 9/10 PCD patients , quantitative analysis was concordant with the `` gold standard '' , while the qualitative evaluation was discordant with the `` gold standard '' in 3/10 cases . Among the patients with an inconclusive `` gold standard '' , the use of quantitative parameters supported PCD diagnosis in 4/9 patients ( confirmed by the identification of disease-causing mutations in one patient ) and PCD exclusion in 2/9 patients . Conclusions : When the beat pattern is normal or virtually immotile , the qualitative evaluation is adequate to study ciliary beating in patients suspected for PCD . However , when cilia are still beating but with moderate alterations ( more than 40 % of patients suspected for PCD ) , quantitative analysis is required to precise the diagnosis and can be proposed to select patients eligible for TEM .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Primary ciliary dyskinesia ( PCD ) is a rare congenital respiratory disorder characterized by abnormal ciliary motility leading to chronic airway infections .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Qualitative evaluation of ciliary beat pattern based on digital high-speed videomicroscopy analysis has been proposed in the diagnosis process of PCD .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Although this evaluation is easy in typical cases ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"it becomes difficult when ciliary beating is partially maintained .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"We postulated that a quantitative analysis of beat pattern would improve PCD diagnosis .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"We compared quantitative parameters with the qualitative evaluation of ciliary beat pattern in patients in whom the diagnosis of PCD was confirmed or excluded .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"Methods : Nasal nitric oxide measurement ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"nasal brushings and biopsies were performed prospectively in 34 patients with suspected PCD .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"In combination with qualitative analysis ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"12 quantitative parameters of ciliary beat pattern were determined on high-speed videomicroscopy recordings of beating ciliated edges .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"The combination of ciliary ultrastructural abnormalities on transmission electron microscopy analysis with low nasal nitric oxide levels was the `` gold standard '' used to establish the diagnosis of PCD .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Results : This `` gold standard '' excluded PCD in 15 patients ( non-PCD patients ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"confirmed PCD in 10 patients ( PCD patients ) and was inconclusive in 9 patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Among the 12 parameters , the distance traveled by the cilium tip weighted by the percentage of beating ciliated edges presented 96 % sensitivity and 95 % specificity .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Qualitative evaluation and quantitative analysis were concordant in non-PCD patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"In 9/10 PCD patients , quantitative analysis was concordant with the `` gold standard '' ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"while the qualitative evaluation was discordant with the `` gold standard '' in 3/10 cases .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Among the patients with an inconclusive `` gold standard '' ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"the use of quantitative parameters supported PCD diagnosis in 4/9 patients ( confirmed by the identification of disease-causing mutations in one patient ) and PCD exclusion in 2/9 patients .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Conclusions : When the beat pattern is normal or virtually immotile ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"the qualitative evaluation is adequate to study ciliary beating in patients suspected for PCD .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"However , when cilia are still beating but with moderate alterations ( more than 40 % of patients suspected for PCD ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 22}, {\"segment_text\": \"quantitative analysis is required to precise the diagnosis and can be proposed to select patients eligible for TEM .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 23}]}"}]}
{"paper_id": "6cc72a73b9f477fdff266f2d74f612132698143e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIn this study , infrared thermography ( IRT ) was assessed as a means of detecting foot-and-mouth disease virus ( FMDV ) - infected cattle before and after the development of clinical signs . Preliminary IRT imaging demonstrated that foot temperatures increased in FMDVinfected animals . The maximum foot temperatures of healthy ( n = 53 ) , directly inoculated ( DI ) ( n = 12 ) , contact ( CT ) ( n = 6 ) , and vaccine trial ( VT ) ( n = 21 ) cattle were measured over the course of FMD infection . A cut-off value was established at 34.4 °C ( sensitivity = 61.1 % , specificity = 87.7 % ) with the aim of detecting FMDV-infected animals both before and after clinical signs were observed . Seven of 12 ( 58 % ) DI and 3/6 ( 50 % ) CT animals showed maximum foot temperatures exceeding the 34.4 °C cut-off before the development of foot vesicles . In contrast , only 5/21 ( 24 % ) VT animals displayed pre-clinical foot temperatures above this cut-off possibly indicating partial vaccine protection of this group . These results show IRT as a promising screening technology to quickly identify potentially infected animals for confirmatory diagnostic testing during FMD outbreaks . Further evaluation of this technology is needed to determine the value of IRT in detecting animals with mild clinical signs or sub-clinical infections . Published by Elsevier Ltd. .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"In this study , infrared thermography ( IRT ) was assessed as a means of detecting foot-and-mouth disease virus ( FMDV ) - infected cattle before and after the development of clinical signs .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Preliminary IRT imaging demonstrated that foot temperatures increased in FMDVinfected animals .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"The maximum foot temperatures of healthy ( n = 53 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 3}, {\"segment_text\": \"directly inoculated ( DI ) ( n = 12 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 4}, {\"segment_text\": \"contact ( CT ) ( n = 6 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"and vaccine trial ( VT ) ( n = 21 ) cattle were measured over the course of FMD infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"A cut-off value was established at 34.4 °C ( sensitivity = 61.1 % , specificity = 87.7 % ) with the aim of detecting FMDV-infected animals both before and after clinical signs were observed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Seven of 12 ( 58 % ) DI and 3/6 ( 50 % ) CT animals showed maximum foot temperatures exceeding the 34.4 °C cut-off before the development of foot vesicles .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"In contrast , only 5/21 ( 24 % ) VT animals displayed pre-clinical foot temperatures above this cut-off possibly indicating partial vaccine protection of this group .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"These results show IRT as a promising screening technology to quickly identify potentially infected animals for confirmatory diagnostic testing during FMD outbreaks .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Further evaluation of this technology is needed to determine the value of IRT in detecting animals with mild clinical signs or sub-clinical infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Published by Elsevier Ltd. .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 12}]}"}]}
{"paper_id": "4b56993a4d0f091e70ef5dec2e5a61c3043f752e", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nMotivation : Accurately determining the atomic structure of proteins represents a fundamental problem in the field of structural bioinformatics . A solution would be significant as protein structure information could be utilized in the medical field , e.g. in the development of vaccines for new viruses . This paper focuses on predicting the protein structure based on 3D images of the proteins captured through cryogenic electron microscopes ( cryo-EM ) . A fully automated computationally efficient protein structure prediction method would be particularly beneficial in the field of cryo-EM as the technology allows researchers to photograph multiple large protein complexes in a single study , which means that a fast prediction method could allow for a high throughput of derived protein structures . We present a deep learning approach , DeepTracer , for predicting locations of the backbone atoms , secondary structure elements , and the amino acid types . In order to connect the predicted amino acids into chains , we applied a modified traveling salesman algorithm . Results : We trained our deep learning model on experimental cryo-EM density maps and tested it on a set of 50 density maps . We found that our new approach predicted protein structures with an average RMSD value of 1.18 and a coverage of 87.5 % . Furthermore , we detected secondary structure information for 87.2 % of amino acids correctly . We also showed preliminarily that 25.2 % of amino acid types could be predicted directly from the 3D cryo-EM density map , considering 20 different types in total . Finally , we noted that the prediction runtime of DeepTracer is significantly improved compared to other methods . It predicts a large protein complex structure of more than 30,000 amino acids in only 2 hours . Availability : The repository of this project will be published . There are two main approaches to predict protein structures : homology modeling and de novo structure prediction . They differ in such that homology modeling requires structural knowledge about a homologous protein for its prediction while de novo methods do not . This limits the\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Motivation : Accurately determining the atomic structure of proteins represents a fundamental problem in the field of structural bioinformatics .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"A solution would be significant as protein structure information could be utilized in the medical field ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"e.g. in the development of vaccines for new viruses .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"This paper focuses on predicting the protein structure based on 3D images of the proteins captured through cryogenic electron microscopes ( cryo-EM ) .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"A fully automated computationally efficient protein structure prediction method would be particularly beneficial in the field of cryo-EM as the technology allows researchers to photograph multiple large protein complexes in a single study ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"which means that a fast prediction method could allow for a high throughput of derived protein structures .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"We present a deep learning approach ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"DeepTracer , for predicting locations of the backbone atoms ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"secondary structure elements , and the amino acid types .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"In order to connect the predicted amino acids into chains ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"we applied a modified traveling salesman algorithm .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"Results : We trained our deep learning model on experimental cryo-EM density maps and tested it on a set of 50 density maps .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"We found that our new approach predicted protein structures with an average RMSD value of 1.18 and a coverage of 87.5 % .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Furthermore , we detected secondary structure information for 87.2 % of amino acids correctly .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"We also showed preliminarily that 25.2 % of amino acid types could be predicted directly from the 3D cryo-EM density map ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"considering 20 different types in total .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Finally , we noted that the prediction runtime of DeepTracer is significantly improved compared to other methods .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"It predicts a large protein complex structure of more than 30,000 amino acids in only 2 hours .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Availability : The repository of this project will be published .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"There are two main approaches to predict protein structures : homology modeling and de novo structure prediction .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"They differ in such that homology modeling requires structural knowledge about a homologous protein for its prediction while de novo methods do not .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}, {\"segment_text\": \"This limits the\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 22}]}"}]}
{"paper_id": "400645d2fdffa9153211848319763984fca6d1b1", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe objectives of the present study were to assess the mucosal , cellular , and humoral immune responses induced by two different infectious bronchitis virus ( IBV ) vaccination regimes and their efficacy against challenge by a variant IBV Q1 . One-day-old broiler chicks were vaccinated with live H120 alone ( group I ) or in combination with CR88 ( group II ) . The two groups were again vaccinated with CR88 at 14 days of age ( doa ) . One group was kept as the control ( group III ) . A significant increase in lachrymal IgA levels was observed at 4 doa and then peaked at 14 doa in the vaccinated groups . The IgA levels in group II were significantly higher than those in group I from 14 doa . Using immunohistochemistry to examine changes in the number of CD4 ؉ and CD8 ؉ cells in the trachea , it was found that overall patterns of CD8 ؉ cells were dominant compared to those of CD4 ؉ cells in the two vaccinated groups . CD8 ؉ cells were significantly higher in group II than those in group I at 21 and 28 doa . All groups were challenged oculonasally with a virulent Q1 strain at 28 doa , and their protection was assessed . The two vaccinated groups gave excellent ciliary protection against Q1 , although group II 's histopathology lesion scores and viral RNA loads in the trachea and kidney showed greater levels of protection than those in group I . These results suggest that greater protection is achieved from the combined vaccination of H120 and CR88 of 1-day-old chicks , followed by CR88 at 14 doa . Citation Chhabra R , Forrester A , Lemiere S , Awad F , Chantrey J , Ganapathy K. 2015 . Mucosal , cellular , and humoral immune responses induced by different live infectious bronchitis virus vaccination regimes and protection conferred against infectious bronchitis virus Q1 strain .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The objectives of the present study were to assess the mucosal ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"cellular , and humoral immune responses induced by two different infectious bronchitis virus ( IBV ) vaccination regimes and their efficacy against challenge by a variant IBV Q1 .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"One-day-old broiler chicks were vaccinated with live H120 alone ( group I ) or in combination with CR88 ( group II ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"The two groups were again vaccinated with CR88 at 14 days of age ( doa ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"One group was kept as the control ( group III ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"A significant increase in lachrymal IgA levels was observed at 4 doa and then peaked at 14 doa in the vaccinated groups .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"The IgA levels in group II were significantly higher than those in group I from 14 doa .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Using immunohistochemistry to examine changes in the number of CD4 ؉ and CD8 ؉ cells in the trachea ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"it was found that overall patterns of CD8 ؉ cells were dominant compared to those of CD4 ؉ cells in the two vaccinated groups .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"CD8 ؉ cells were significantly higher in group II than those in group I at 21 and 28 doa .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"All groups were challenged oculonasally with a virulent Q1 strain at 28 doa ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and their protection was assessed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"The two vaccinated groups gave excellent ciliary protection against Q1 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"although group II 's histopathology lesion scores and viral RNA loads in the trachea and kidney showed greater levels of protection than those in group I .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"These results suggest that greater protection is achieved from the combined vaccination of H120 and CR88 of 1-day-old chicks ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"followed by CR88 at 14 doa .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Citation Chhabra R , Forrester A ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 17}, {\"segment_text\": \"Lemiere S , Awad F ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 18}, {\"segment_text\": \"Chantrey J , Ganapathy K. 2015 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 19}, {\"segment_text\": \"Mucosal , cellular , and humoral immune responses induced by different live infectious bronchitis virus vaccination regimes and protection conferred against infectious bronchitis virus Q1 strain .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 20}]}"}]}
{"paper_id": "ed638b6b8897dfcc7b28ba26c2bb6048da0501e6", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nObjectives We used data from the Global Burden of Disease 2015 study ( GBD ) to calculate the burden of lower respiratory infections ( LRIs ) in the 22 countries of the Eastern Mediterranean Region ( EMR ) from 1990 to 2015 . Methods We conducted a systematic analysis of mortality and morbidity data for LRI and its specific etiologic factors , including pneumococcus , Haemophilus influenzae type b , Respiratory syncytial virus , and influenza virus . We used modeling methods to estimate incidence , deaths , and disability-adjusted life-years ( DALYs ) . We calculated burden attributable to known risk factors for LRI . Results In 2015 , LRIs were the fourth-leading cause of DALYs , causing 11,098,243 ( 95 % UI 9,857,095-12,396,566 ) DALYs and 191,114 ( 95 % UI 170,705 ) deaths . The LRI DALY rates were higher than global estimates in 2015 . The highest and lowest age-standardized rates of DALYs were observed in Somalia and Lebanon , respectively . Undernutrition in childhood and ambient particulate matter air pollution in the elderly were the main risk factors . Conclusions Our findings call for public health strategies to reduce the level of risk factors in each age group , especially vulnerable child and elderly populations .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Objectives We used data from the Global Burden of Disease 2015 study ( GBD ) to calculate the burden of lower respiratory infections ( LRIs ) in the 22 countries of the Eastern Mediterranean Region ( EMR ) from 1990 to 2015 .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 1}, {\"segment_text\": \"Methods We conducted a systematic analysis of mortality and morbidity data for LRI and its specific etiologic factors ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"including pneumococcus , Haemophilus influenzae type b ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Respiratory syncytial virus , and influenza virus .\", \"label\": \"method\", \"decision_reference\": \"method.definition\", \"id\": 4}, {\"segment_text\": \"We used modeling methods to estimate incidence ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"deaths , and disability-adjusted life-years ( DALYs ) .\", \"label\": \"method\", \"decision_reference\": \"method.definition\", \"id\": 6}, {\"segment_text\": \"We calculated burden attributable to known risk factors for LRI .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Results In 2015 , LRIs were the fourth-leading cause of DALYs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"causing 11,098,243 ( 95 % UI 9,857,095-12,396,566 ) DALYs and 191,114 ( 95 % UI 170,705 ) deaths .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"The LRI DALY rates were higher than global estimates in 2015 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"The highest and lowest age-standardized rates of DALYs were observed in Somalia and Lebanon , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Undernutrition in childhood and ambient particulate matter air pollution in the elderly were the main risk factors .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Conclusions Our findings call for public health strategies to reduce the level of risk factors in each age group ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"especially vulnerable child and elderly populations .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}]}"}]}
{"paper_id": "93244303c6041ad53fcc59cc06a03cc51621edcc", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSevere viral infections , including hemorrhagic fever and encephalitis , occur throughout the world , but are most prevalent in developing areas that are most vulnerable to infectious diseases . Some of these can also infect related species as illustrated by the threatened extinction of gorillas by Ebola infection in west and central Africa . There are no safe and effective treatments available for these serious infections . In addition to the logistical difficulties inherent in developing a drug for infections that are sporadic and occur mainly in the third world , there is the overwhelming barrier of no hope for return on investment to encourage the pharmaceutical industry to address these unmet medical needs . Therefore , the National Institute of Allergy and infectious Disease ( NIAID ) has developed and supported a variety of programs and resources to provide assistance and lower the barrier for those who undertake these difficult challenges . The primary programs relevant to the development of therapies for severe viral infections are described and three case studies illustrate how they have been used . In addition , contact information for accessing these resources is supplied . Published by Elsevier B.V.\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Severe viral infections , including hemorrhagic fever and encephalitis ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"occur throughout the world , but are most prevalent in developing areas that are most vulnerable to infectious diseases .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Some of these can also infect related species as illustrated by the threatened extinction of gorillas by Ebola infection in west and central Africa .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"There are no safe and effective treatments available for these serious infections .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"In addition to the logistical difficulties inherent in developing a drug for infections that are sporadic and occur mainly in the third world ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"there is the overwhelming barrier of no hope for return on investment to encourage the pharmaceutical industry to address these unmet medical needs .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Therefore , the National Institute of Allergy and infectious Disease ( NIAID ) has developed and supported a variety of programs and resources to provide assistance and lower the barrier for those who undertake these difficult challenges .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"The primary programs relevant to the development of therapies for severe viral infections are described and three case studies illustrate how they have been used .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"In addition , contact information for accessing these resources is supplied .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Published by Elsevier B.V.\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 10}]}"}]}
{"paper_id": "84fb34996678d2b07b936892fc9c445fe7944148", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\n. Intranasal inoculation with mouse hepatitis virus strain JHM MHV-JHM results in acute meningoencephalitis . We found NOS II mRNA expression in brains of acutely infected animals on days 5 through 7 after infection . In situ hybridization and immunohistochemistry demonstrated NOS II message and protein in infiltrating macrophages . Persistent infection with MHV-JHM results in chronic demyelinating encephalomyelitis . NOS II mRNA was detected in persistently infected spinal cords . In situ hybridization and immunohistochemistry showed expression of NOS II in astrocytes in and around demyelinated lesions . These results suggest the role of NO release in acute versus persistent infection with this virus , and its contribution to the resulting pathology , may be different .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \".\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 1}, {\"segment_text\": \"Intranasal inoculation with mouse hepatitis virus strain JHM MHV-JHM results in acute meningoencephalitis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"We found NOS II mRNA expression in brains of acutely infected animals on days 5 through 7 after infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"In situ hybridization and immunohistochemistry demonstrated NOS II message and protein in infiltrating macrophages .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Persistent infection with MHV-JHM results in chronic demyelinating encephalomyelitis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"NOS II mRNA was detected in persistently infected spinal cords .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"In situ hybridization and immunohistochemistry showed expression of NOS II in astrocytes in and around demyelinated lesions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"These results suggest the role of NO release in acute versus persistent infection with this virus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"and its contribution to the resulting pathology , may be different .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}]}"}]}
{"paper_id": "a510ff06475118256003b81fbc9abdaa33242da1", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nVerdier de K , Öhagen P , Alenius S : No effect of a homeopathic preparation on neonatal calf diarrhoea in a randomised double-blind placebo-controlled clinical trial . Acta vet . scand . 2003 , 44 , 97-101 . - A double-blind , placebo-controlled clinical trial of a homeopathic treatment of neonatal calf diarrhoea was performed using 44 calves in 12 dairy herds . Calves with spontaneously derived diarrhoea were treated with either the homeopathic remedy Podophyllum ( D30 ) ( n = 24 ) or a placebo ( n = 20 ) . No clinically or statistically significant difference between the 2 groups was demonstrated . Calves treated with Podophyllum had an average of 3.1 days of diarrhoea compared with 2.9 days for the placebo group . Depression , inappetence and fever were presented equally in the 2 groups . These results support the widely held opinion that scientific proof for the efficacy of veterinary homeopathy is lacking . In the European Union this implies a considerable risk for animal welfare , since in some countries priority is given to homeopathic treatments in organic farming .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Verdier de K , Öhagen P ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 1}, {\"segment_text\": \"Alenius S : No effect of a homeopathic preparation on neonatal calf diarrhoea in a randomised double-blind placebo-controlled clinical trial .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Acta vet .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 3}, {\"segment_text\": \"scand .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 4}, {\"segment_text\": \"2003 , 44 , 97-101 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 5}, {\"segment_text\": \"- A double-blind , placebo-controlled clinical trial of a homeopathic treatment of neonatal calf diarrhoea was performed using 44 calves in 12 dairy herds .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Calves with spontaneously derived diarrhoea were treated with either the homeopathic remedy Podophyllum ( D30 ) ( n = 24 ) or a placebo ( n = 20 ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"No clinically or statistically significant difference between the 2 groups was demonstrated .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Calves treated with Podophyllum had an average of 3.1 days of diarrhoea compared with 2.9 days for the placebo group .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Depression , inappetence and fever were presented equally in the 2 groups .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"These results support the widely held opinion that scientific proof for the efficacy of veterinary homeopathy is lacking .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"In the European Union this implies a considerable risk for animal welfare ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"since in some countries priority is given to homeopathic treatments in organic farming .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "8c774253bbaeafa603da15f75f290153e09a3858", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\n| Zoonotic spillover , which is the transmission of a pathogen from a vertebrate animal to a human , presents a global public health burden but is a poorly understood phenomenon . Zoonotic spillover requires several factors to align , including the ecological , epidemiological and behavioural determinants of pathogen exposure , and the within-human factors that affect susceptibility to infection . In this Opinion article , we propose a synthetic framework for animal-to-human transmission that integrates the relevant mechanisms . This framework reveals that all zoonotic pathogens must overcome a hierarchical series of barriers to cause spillover infections in humans . Understanding how these barriers are functionally and quantitatively linked , and how they interact in space and time , will substantially improve our ability to predict or prevent spillover events . This work provides a foundation for transdisciplinary investigation of spillover and synthetic theory on zoonotic transmission . 502 | AUGUST 2017 | VOLUME 15 www.nature.com/nrmicro PERSPECTIVES © 2 0 1 7 M a c m i l l a n P u b l i s h e r s L i m i t e d , p a r t o f S p r i n g e r N a t u r e . A l l r i g h t s r e s e r v e d . NATURE REVIEWS | MICROBIOLOGY VOLUME 15 | AUGUST 2017 | 503 © 2 0 1 7 M a c m i l l a n P u b l i s h e r s L i m i t e d , p a r t o f S p r i n g e r N a t u r e . A l l r i g h t s r e s e\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"| Zoonotic spillover , which is the transmission of a pathogen from a vertebrate animal to a human ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"presents a global public health burden but is a poorly understood phenomenon .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Zoonotic spillover requires several factors to align ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"including the ecological , epidemiological and behavioural determinants of pathogen exposure ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"and the within-human factors that affect susceptibility to infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"In this Opinion article , we propose a synthetic framework for animal-to-human transmission that integrates the relevant mechanisms .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"This framework reveals that all zoonotic pathogens must overcome a hierarchical series of barriers to cause spillover infections in humans .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Understanding how these barriers are functionally and quantitatively linked ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"and how they interact in space and time ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"will substantially improve our ability to predict or prevent spillover events .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"This work provides a foundation for transdisciplinary investigation of spillover and synthetic theory on zoonotic transmission .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"502 | AUGUST 2017 | VOLUME 15 www.nature.com/nrmicro PERSPECTIVES © 2 0 1 7 M a c m i l l a n P u b l i s h e r s L i m i t e d ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 12}, {\"segment_text\": \"p a r t o f S p r i n g e r N a t u r e .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 13}, {\"segment_text\": \"A l l r i g h t s r e s e r v e d .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 14}, {\"segment_text\": \"NATURE REVIEWS | MICROBIOLOGY VOLUME 15 | AUGUST 2017 | 503 © 2 0 1 7 M a c m i l l a n P u b l i s h e r s L i m i t e d ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 15}, {\"segment_text\": \"p a r t o f S p r i n g e r N a t u r e .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 16}, {\"segment_text\": \"A l l r i g h t s r e s e\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 17}]}"}]}
{"paper_id": "e7c418a0ed3500943dcc6d2edf9dae908b60e828", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAn enzyme-linked immunosorhent assay ( ELISA ) which detects rhinovirus specific antibody in human sera and nasal secretions . has been developed . This sandwich ELISA utilizes a rabbit antirhinovirus hyperimmune serum as the capture antibody and was found to he very sensitive , detecting rhinovirus specific antibody in the serum at dilutions of 1 : 1tY ' and 1 : 10 ' ' for IgG and IgA immunoglobulins , respectively . Thus , this new assay is lo ' -10 J times more sensitive than our standard neutralization test . Furthermore . this increase in sensitivity has enabled us to reliably detect rhinovirus specific immunoglobulins in unconcentrated nasal washings , which are thought to he particularly important for protection against rhinovirus reinfection . A preliminary study of the immune response in human volunteers challenged with rhinovirus using this new ELISA system is presented and further applications and potential of the method are also discussed .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"An enzyme-linked immunosorhent assay ( ELISA ) which detects rhinovirus specific antibody in human sera and nasal secretions .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"has been developed .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"This sandwich ELISA utilizes a rabbit antirhinovirus hyperimmune serum as the capture antibody and was found to he very sensitive ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"detecting rhinovirus specific antibody in the serum at dilutions of 1 : 1tY ' and 1 : 10 ' ' for IgG and IgA immunoglobulins , respectively .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Thus , this new assay is lo ' -10 J times more sensitive than our standard neutralization test .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Furthermore .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"this increase in sensitivity has enabled us to reliably detect rhinovirus specific immunoglobulins in unconcentrated nasal washings ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"which are thought to he particularly important for protection against rhinovirus reinfection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"A preliminary study of the immune response in human volunteers challenged with rhinovirus using this new ELISA system is presented and further applications and potential of the method are also discussed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}]}"}]}
{"paper_id": "c6b2ffc5a86ad4dd61bdc1ff6aaea7bacf824679", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground . Experimental inoculation is an important tool for common cold and asthma research . Producing rhinovirus ( RV ) inocula from nasal secretions has required prolonged observation of the virus donor to exclude extraneous pathogens . We produced a RV-A16 inoculum using reverse genetics and determined the dose necessary to cause moderate colds in seronegative volunteers . Methods . The consensus sequence of RV-A16 from a previous inoculum was cloned , and inoculum virus was produced using reverse genetics techniques . After safety testing , volunteers were inoculated with either RV-A16 ( n = 26 ) or placebo ( n = 10 ) , Jackson cold scores were recorded , and nasal secretions were tested for shedding of RV-A16 ribonucleic acid . Results . The reverse genetics process produced infectious virus that was neutralized by specific antisera and had a mutation rate similar to conventional virus growth techniques . The 1000 median tissue culture infectious dose ( TCID 50 ) dose produced moderate colds in most individuals with effects similar to that of a previously tested conventional RV-A16 inoculum . Conclusions . Reverse genetics techniques produced a RV-A16 inoculum that can cause clinical colds in seronegative volunteers , and they also serve as a stable source of virus for laboratory use . The recombinant production procedures eliminate the need to derive seed virus from nasal secretions , thus precluding introduction of extraneous pathogens through this route .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Experimental inoculation is an important tool for common cold and asthma research .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Producing rhinovirus ( RV ) inocula from nasal secretions has required prolonged observation of the virus donor to exclude extraneous pathogens .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"We produced a RV-A16 inoculum using reverse genetics and determined the dose necessary to cause moderate colds in seronegative volunteers .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Methods .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"The consensus sequence of RV-A16 from a previous inoculum was cloned ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"and inoculum virus was produced using reverse genetics techniques .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"After safety testing , volunteers were inoculated with either RV-A16 ( n = 26 ) or placebo ( n = 10 ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Jackson cold scores were recorded ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"and nasal secretions were tested for shedding of RV-A16 ribonucleic acid .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Results .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"The reverse genetics process produced infectious virus that was neutralized by specific antisera and had a mutation rate similar to conventional virus growth techniques .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"The 1000 median tissue culture infectious dose ( TCID 50 ) dose produced moderate colds in most individuals with effects similar to that of a previously tested conventional RV-A16 inoculum .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Conclusions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Reverse genetics techniques produced a RV-A16 inoculum that can cause clinical colds in seronegative volunteers ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"and they also serve as a stable source of virus for laboratory use .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"The recombinant production procedures eliminate the need to derive seed virus from nasal secretions ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"thus precluding introduction of extraneous pathogens through this route .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "a3ff62cdc7cd33bb6618950b28fe649bf95ef6de", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nConclusions Adenovirus is frequently detected with other respiratory viruses . Persons with non-C adenovirus infections reported more severe symptoms , suggesting there may be speciesspecific differences in virulence and/or host response to infection .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Conclusions Adenovirus is frequently detected with other respiratory viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 1}, {\"segment_text\": \"Persons with non-C adenovirus infections reported more severe symptoms ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"suggesting there may be speciesspecific differences in virulence and/or host response to infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}]}"}]}
{"paper_id": "3e5cc874ecacef64da59d6a771939c385ff3710d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSingle-sided natural ventilation was numerically investigated to determine the impact of buoyancy and wind on the cross-transmission of pollution by considering six window types commonly found in multistory buildings . The goal of this study was to predict the gaseous pollutant transmission using computational fluid dynamics based on the Reynolds-averaged Navier-Stokes equations and baseline k-ω turbulence equations . The results indicated that ventilation rates generally increased with increasing wind speeds if the effects of buoyancy and wind were not suppressed ; however , the re-entry ratio representing the proportion of expelled air re-entering other floors and the corresponding risk of infection decreased . If the source of the virus was on a central floor , the risk of infection was the highest on the floors closest to the source . Different window types were also considered for determining their effectiveness in controlling cross-transmission and infection risk , depending on the source location and driving force ( e.g. , buoyancy and wind ) .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Single-sided natural ventilation was numerically investigated to determine the impact of buoyancy and wind on the cross-transmission of pollution by considering six window types commonly found in multistory buildings .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"The goal of this study was to predict the gaseous pollutant transmission using computational fluid dynamics based on the Reynolds-averaged Navier-Stokes equations and baseline k-ω turbulence equations .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 2}, {\"segment_text\": \"The results indicated that ventilation rates generally increased with increasing wind speeds if the effects of buoyancy and wind were not suppressed ; however ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"the re-entry ratio representing the proportion of expelled air re-entering other floors and the corresponding risk of infection decreased .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"If the source of the virus was on a central floor ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"the risk of infection was the highest on the floors closest to the source .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Different window types were also considered for determining their effectiveness in controlling cross-transmission and infection risk ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"depending on the source location and driving force ( e.g. , buoyancy and wind ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}]}"}]}
{"paper_id": "1b1d99b4ffc25a1c74d8db98063c690dd02a8e2c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nEven after one hundred years , the Golgi apparatus remains a major challenge in the field of Cell Biology . This is particularly true in terms of transport and of protein sorting . For example , the question how cargo proteins are transported through this organelle is still a matter of debate . Emphasis has been put on the role of anterograde and retrograde transport vesicles . These have been proposed to carry cargo from cisterna to cisterna and to recycle components needed for further rounds of transport . Alternatively , anterograde movement of cargo takes place in cisternal membranes rather than transport vesicles . These membranes assemble and mature in a cis to trans direction . In this case , retrograde transport vesicles need to recycle all components of the Golgi apparatus and this demands a highly dynamic and efficient sorting machinery . Here we will discuss possible mechanisms for protein sorting in the context of cisternal maturation and propose that a common mechanism is sufficient to explain both transport of cargo and sorting of resident proteins . ß 1998 Elsevier Science B.V. All rights reserved .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Even after one hundred years ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"the Golgi apparatus remains a major challenge in the field of Cell Biology .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"This is particularly true in terms of transport and of protein sorting .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"For example , the question how cargo proteins are transported through this organelle is still a matter of debate .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Emphasis has been put on the role of anterograde and retrograde transport vesicles .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"These have been proposed to carry cargo from cisterna to cisterna and to recycle components needed for further rounds of transport .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Alternatively , anterograde movement of cargo takes place in cisternal membranes rather than transport vesicles .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"These membranes assemble and mature in a cis to trans direction .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"In this case , retrograde transport vesicles need to recycle all components of the Golgi apparatus and this demands a highly dynamic and efficient sorting machinery .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"Here we will discuss possible mechanisms for protein sorting in the context of cisternal maturation and propose that a common mechanism is sufficient to explain both transport of cargo and sorting of resident proteins .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 10}, {\"segment_text\": \"ß 1998 Elsevier Science B.V. All rights reserved .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 11}]}"}]}
{"paper_id": "2a660aed307955e8b1b74da18aef9c95c68f0cf0", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nNeuroadapted Sindbis virus infection of mice causes T cell-mediated fatal encephalomyelitis . In the absence of IL-10 , pathogenic Th17 cells are increased and disease is accelerated . Lymphoid and myeloid cell contributions to IL-10 production were determined using VertX IL-10 transcriptional eGFP reporter mice . Effector and regulatory CD4 + and CD8 + T cells in the brain , but not the cervical lymph nodes , were the primary producers of IL-10 . Th17 and Th1/Th17 cells were increased in mice that lacked T cell IL-10 production , although less than in the absence of IL-10 . Morbidity and mortality were not affected suggesting an IL-10 threshold for disease exacerbation .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Neuroadapted Sindbis virus infection of mice causes T cell-mediated fatal encephalomyelitis .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"In the absence of IL-10 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"pathogenic Th17 cells are increased and disease is accelerated .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Lymphoid and myeloid cell contributions to IL-10 production were determined using VertX IL-10 transcriptional eGFP reporter mice .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Effector and regulatory CD4 + and CD8 + T cells in the brain ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"but not the cervical lymph nodes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"were the primary producers of IL-10 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Th17 and Th1/Th17 cells were increased in mice that lacked T cell IL-10 production ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"although less than in the absence of IL-10 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Morbidity and mortality were not affected suggesting an IL-10 threshold for disease exacerbation .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}]}"}]}
{"paper_id": "6d19865af9d32dba5e90bd15a21aabe0c8ac5157", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nIn this study , we isolated and characterized an insect nidovirus from the mosquito Culex tritaeniorhynchus Giles ( Diptera : Culicidae ) in Vietnam , as an additional member of the new family Mesoniviridae in the order Nidovirales . The virus , designated `` Dak Nong virus ( DKNV ) , '' shared many characteristics with Cavally virus and Nam Dinh virus , which have also been discovered recently in mosquitoes , and these viruses should be considered members of a single virus species , Alphamesonivirus 1 . DKNV grew in cultured mosquito cells but could not replicate in the cultured vertebrate cells tested . N-terminal sequencing of the DKNV structural proteins revealed two posttranslational cleavage sites in the spike glycoprotein precursor . DKNV is assumed to be a new member of the species Alphamesonivirus 1 , and the current study provides further understanding of viruses belonging to the new family Mesoniviridae . R. Kuwata and T. Satho contributed equally .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"In this study , we isolated and characterized an insect nidovirus from the mosquito Culex tritaeniorhynchus Giles ( Diptera : Culicidae ) in Vietnam ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 1}, {\"segment_text\": \"as an additional member of the new family Mesoniviridae in the order Nidovirales .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"The virus , designated `` Dak Nong virus ( DKNV ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"'' shared many characteristics with Cavally virus and Nam Dinh virus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"which have also been discovered recently in mosquitoes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"and these viruses should be considered members of a single virus species , Alphamesonivirus 1 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"DKNV grew in cultured mosquito cells but could not replicate in the cultured vertebrate cells tested .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"N-terminal sequencing of the DKNV structural proteins revealed two posttranslational cleavage sites in the spike glycoprotein precursor .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"DKNV is assumed to be a new member of the species Alphamesonivirus 1 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"and the current study provides further understanding of viruses belonging to the new family Mesoniviridae .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"R. Kuwata and T. Satho contributed equally .\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 11}]}"}]}
{"paper_id": "b41f3634a764bf08cbc4588f37d7d422a02fa541", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Since the 9/11 attack and severe acute respiratory syndrome ( SARS ) , the development of qualified and able public health leaders has become a new urgency in building the infrastructure needed to address public health emergencies . Although previous studies have reported that the training of individual leaders is an important approach , the systemic and scientific training model need further improvement and development . The purpose of this study was to develop , deliver , and evaluate a participatory leadership training program for emergency response . Methods : Forty-one public health leaders ( N = 41 ) from five provinces completed the entire emergency preparedness training program in China . The program was evaluated by anonymous questionnaires and semi-structured interviews held prior to training , immediately post-training and 12-month after training ( Follow-up ) . The emergency preparedness training resulted in positive shifts in knowledge , selfassessment of skills for public health leaders . More than ninety-five percent of participants reported that the training model was scientific and feasible . Moreover , the response of participants in the program to the avian influenza outbreak , as well as the planned evaluations for this leadership training program , further demonstrated both the successful approaches and methods and the positive impact of this integrated leadership training initiative . The emergency preparedness training program met its aims and objectives satisfactorily , and improved the emergency capability of public health leaders . This suggests that the leadership training model was effective and feasible in improving the emergency preparedness capability .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Since the 9/11 attack and severe acute respiratory syndrome ( SARS ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"the development of qualified and able public health leaders has become a new urgency in building the infrastructure needed to address public health emergencies .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Although previous studies have reported that the training of individual leaders is an important approach ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"the systemic and scientific training model need further improvement and development .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"The purpose of this study was to develop ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"deliver , and evaluate a participatory leadership training program for emergency response .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"Methods : Forty-one public health leaders ( N = 41 ) from five provinces completed the entire emergency preparedness training program in China .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"The program was evaluated by anonymous questionnaires and semi-structured interviews held prior to training ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"immediately post-training and 12-month after training ( Follow-up ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"The emergency preparedness training resulted in positive shifts in knowledge ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"selfassessment of skills for public health leaders .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"More than ninety-five percent of participants reported that the training model was scientific and feasible .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"Moreover , the response of participants in the program to the avian influenza outbreak ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"as well as the planned evaluations for this leadership training program ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"further demonstrated both the successful approaches and methods and the positive impact of this integrated leadership training initiative .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"The emergency preparedness training program met its aims and objectives satisfactorily ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"and improved the emergency capability of public health leaders .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"This suggests that the leadership training model was effective and feasible in improving the emergency preparedness capability .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}]}"}]}
{"paper_id": "ceb20b553bb8bf847fc4b72d555836e7ccc4403d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : The epidemiology of Mycoplasma pneumoniae ( MP ) and local dominant etiologies of pathogens that cause respiratory tract infections ( RTIs ) among central China children ( ≤ 14 years old ) hospitalized are poorly understood . Methods : A total of 10,429 specimens were analyzed , and IgM antibodies against 9 respiratory pathogens including MP were detected using indirect immunofluorescence assay from serum . Results : It showed that 59.3 % of the enrolled children were positive for at least 1 pathogen ; highest detection rates included those between 3 and < 6 years of age ( 70.4 % ) , female ( 63.2 % ) , and who were hospitalized in 2014 ( 80.9 % ) . The most predominant pathogen was MP ( 45.6 % ) , followed by Parainfluenza viruses ( PIVs ) ( 22.6 % ) and influenza B viruses ( IFVB ) ( 14.7 % ) . Coinfection was observed in 2,907 specimens ( 27.9 % ) ; the coinfection combination containing MP and PIVs had the highest detection rate of 15 % , followed by MP and IFVB as well as IFVB and PIVs . Conclusions : MP was the most commonly detected bacteria among hospitalized children , which should be included in the differential diagnosis for hospitalized children with RTI . These findings will contribute to the effective prevention and therapeutic approaches of pathogens among local children suffering from RTI .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : The epidemiology of Mycoplasma pneumoniae ( MP ) and local dominant etiologies of pathogens that cause respiratory tract infections ( RTIs ) among central China children ( ≤ 14 years old ) hospitalized are poorly understood .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Methods : A total of 10,429 specimens were analyzed ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"and IgM antibodies against 9 respiratory pathogens including MP were detected using indirect immunofluorescence assay from serum .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Results : It showed that 59.3 % of the enrolled children were positive for at least 1 pathogen ; highest detection rates included those between 3 and < 6 years of age ( 70.4 % ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 4}, {\"segment_text\": \"female ( 63.2 % ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 5}, {\"segment_text\": \"and who were hospitalized in 2014 ( 80.9 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"The most predominant pathogen was MP ( 45.6 % ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"followed by Parainfluenza viruses ( PIVs ) ( 22.6 % ) and influenza B viruses ( IFVB ) ( 14.7 % ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"Coinfection was observed in 2,907 specimens ( 27.9 % ) ; the coinfection combination containing MP and PIVs had the highest detection rate of 15 % ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"followed by MP and IFVB as well as IFVB and PIVs .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"Conclusions : MP was the most commonly detected bacteria among hospitalized children ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"which should be included in the differential diagnosis for hospitalized children with RTI .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"These findings will contribute to the effective prevention and therapeutic approaches of pathogens among local children suffering from RTI .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "b54cb4255fa62b88defc1f51d8fc3273d808b9fc", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nDuring viral and bacterial infections , the innate immune system recognizes various types of pathogen-associated molecular patterns ( PAMPs ) , such as nucleic acids , via a series of membrane-bound or cytosolic pattern-recognition receptors . These include Toll-like receptors ( TLRs ) , RIG-I-like receptors ( RLRs ) , AIM2-like receptors ( ALRs ) , and cytosolic DNA sensors . The binding of PAMPs to these receptors triggers the production of type I interferon ( IFN ) and inflammatory cytokines . Type I IFN induces the expression of interferon stimulated genes ( ISGs ) , which protect surrounding cells from infection . Some ISGs are nucleic acids-binding proteins that bind viral nucleic acids and suppress their replication . As nucleic acids are essential components that store and transmit genetic information in every species , infectious pathogens have developed systems to escape from the host nucleic acid recognition system . Host cells also have their own nucleic acids that are frequently released to the extracellular milieu or the cytoplasm during cell death or stress responses , which , if able to bind pattern-recognition receptors , would induce autoimmunity and inflammation . Therefore , host cells have acquired mechanisms to protect themselves from contact with their own nucleic acids . In this review , we describe recent research progress into the nucleic acid recognition mechanism and the molecular bases of discrimination between self and non-self-nucleic acids .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"During viral and bacterial infections ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"the innate immune system recognizes various types of pathogen-associated molecular patterns ( PAMPs ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"such as nucleic acids , via a series of membrane-bound or cytosolic pattern-recognition receptors .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"These include Toll-like receptors ( TLRs ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"RIG-I-like receptors ( RLRs ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"AIM2-like receptors ( ALRs ) , and cytosolic DNA sensors .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"The binding of PAMPs to these receptors triggers the production of type I interferon ( IFN ) and inflammatory cytokines .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Type I IFN induces the expression of interferon stimulated genes ( ISGs ) ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"which protect surrounding cells from infection .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"Some ISGs are nucleic acids-binding proteins that bind viral nucleic acids and suppress their replication .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"As nucleic acids are essential components that store and transmit genetic information in every species ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"infectious pathogens have developed systems to escape from the host nucleic acid recognition system .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 12}, {\"segment_text\": \"Host cells also have their own nucleic acids that are frequently released to the extracellular milieu or the cytoplasm during cell death or stress responses ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 13}, {\"segment_text\": \"which , if able to bind pattern-recognition receptors ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 14}, {\"segment_text\": \"would induce autoimmunity and inflammation .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 15}, {\"segment_text\": \"Therefore , host cells have acquired mechanisms to protect themselves from contact with their own nucleic acids .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"In this review , we describe recent research progress into the nucleic acid recognition mechanism and the molecular bases of discrimination between self and non-self-nucleic acids .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "54943a77892dcdfac090664c4c09ff219b28c6d7", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nSimultaneous extraction and separation of liquiritin , glycyrrhizic acid , and glabridin from licorice were developed by liquidliquid extraction with liquid chromatography separation . By utilizing different extraction solvents , procedures , and times , the optimum extraction conditions were established . The extracts of licorice were separated and determined using a C 18 column with a mobile phase consisting of acetonitrile-water ( containing 1.0 % acetic acid ) with a gradient elution of 0 ~ 10 min from 20:80 to 60:40 ( v/v ) . Preparative columns with different packing sizes were investigated to isolate the three compounds from the extracts of licorice . The 12 μm chromatographic column showed better separation for the three compounds from licorice . 0.29 mg/g for liquiritin , 1.43 mg/g for glycyrrhizic acid , and 0.07 mg/g for glabridin were obtained and the recoveries were 80.8 , 89.7 , and 72.5 % , respectively . © KSBB\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Simultaneous extraction and separation of liquiritin ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"glycyrrhizic acid , and glabridin from licorice were developed by liquidliquid extraction with liquid chromatography separation .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"By utilizing different extraction solvents ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"procedures , and times , the optimum extraction conditions were established .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"The extracts of licorice were separated and determined using a C 18 column with a mobile phase consisting of acetonitrile-water ( containing 1.0 % acetic acid ) with a gradient elution of 0 ~ 10 min from 20:80 to 60:40 ( v/v ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"Preparative columns with different packing sizes were investigated to isolate the three compounds from the extracts of licorice .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"The 12 μm chromatographic column showed better separation for the three compounds from licorice .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"0.29 mg/g for liquiritin , 1.43 mg/g for glycyrrhizic acid ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"and 0.07 mg/g for glabridin were obtained and the recoveries were 80.8 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"89.7 , and 72.5 % , respectively .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"© KSBB\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 11}]}"}]}
{"paper_id": "3568da162b8d9f5356c9264193b6292efa3d9556", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe gene expression of plus-strand RNA viruses with a polycistronic genome depends on translation and replication of the genomic mRNA , as well as synthesis of subgenomic ( sg ) mRNAs . Arteriviruses and coronaviruses , distantly related members of the nidovirus order , employ a unique mechanism of discontinuous minus-strand RNA synthesis to generate subgenomelength templates for the synthesis of a nested set of sg mRNAs . Non-structural protein 1 ( nsp1 ) of the arterivirus equine arteritis virus ( EAV ) , a multifunctional regulator of viral RNA synthesis and virion biogenesis , was previously implicated in controlling the balance between genome replication and sg mRNA synthesis . Here , we employed reverse and forward genetics to gain insight into the multiple regulatory roles of nsp1 . Our analysis revealed that the relative abundance of viral mRNAs is tightly controlled by an intricate network of interactions involving all nsp1 subdomains . Distinct nsp1 mutations affected the quantitative balance among viral mRNA species , and our data implicate nsp1 in controlling the accumulation of full-length and subgenome-length minus-strand templates for viral mRNA synthesis . The moderate differential changes in viral mRNA abundance of nsp1 mutants resulted in similarly altered viral protein levels , but progeny virus yields were greatly reduced . Pseudorevertant analysis provided compelling genetic evidence that balanced EAV mRNA accumulation is critical for efficient virus production . This first report on protein-mediated , mRNA-specific control of nidovirus RNA synthesis reveals the existence of an integral control mechanism to fine-tune replication , sg mRNA synthesis , and virus production , and establishes a major role for nsp1 in coordinating the arterivirus replicative cycle . Citation : Nedialkova DD , Gorbalenya AE , Snijder EJ ( 2010 ) Arterivirus Nsp1 Modulates the Accumulation of Minus-Strand Templates to Control the Relative Abundance of Viral mRNAs . PLoS Pathog 6 ( 2 ) : e1000772 .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The gene expression of plus-strand RNA viruses with a polycistronic genome depends on translation and replication of the genomic mRNA ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"as well as synthesis of subgenomic ( sg ) mRNAs .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Arteriviruses and coronaviruses , distantly related members of the nidovirus order ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"employ a unique mechanism of discontinuous minus-strand RNA synthesis to generate subgenomelength templates for the synthesis of a nested set of sg mRNAs .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Non-structural protein 1 ( nsp1 ) of the arterivirus equine arteritis virus ( EAV ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"a multifunctional regulator of viral RNA synthesis and virion biogenesis ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"was previously implicated in controlling the balance between genome replication and sg mRNA synthesis .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"Here , we employed reverse and forward genetics to gain insight into the multiple regulatory roles of nsp1 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Our analysis revealed that the relative abundance of viral mRNAs is tightly controlled by an intricate network of interactions involving all nsp1 subdomains .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Distinct nsp1 mutations affected the quantitative balance among viral mRNA species ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"and our data implicate nsp1 in controlling the accumulation of full-length and subgenome-length minus-strand templates for viral mRNA synthesis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"The moderate differential changes in viral mRNA abundance of nsp1 mutants resulted in similarly altered viral protein levels ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"but progeny virus yields were greatly reduced .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Pseudorevertant analysis provided compelling genetic evidence that balanced EAV mRNA accumulation is critical for efficient virus production .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"This first report on protein-mediated ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"mRNA-specific control of nidovirus RNA synthesis reveals the existence of an integral control mechanism to fine-tune replication ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"sg mRNA synthesis , and virus production ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"and establishes a major role for nsp1 in coordinating the arterivirus replicative cycle .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Citation : Nedialkova DD , Gorbalenya AE ,\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 19}, {\"segment_text\": \"Snijder EJ ( 2010 ) Arterivirus Nsp1 Modulates the Accumulation of Minus-Strand Templates to Control the Relative Abundance of Viral mRNAs .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 20}, {\"segment_text\": \"PLoS Pathog 6 ( 2 ) : e1000772 .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 21}]}"}]}
{"paper_id": "9cfd956a4bf5b1ad8f07f07f89fb38f261965970", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nAn enzyme-linked immunosorbent assays ( ELISA ) based on recombinant nucleocapsid ( N ) protein generated in Escherichia coli was evaluated for its sensitivity and specificity for diagnosis of porcine epidemic diarrhea ( PEDV ) infection . The N gene encoding the N protein was cloned and expressed as a fusion protein with His tag protein in E. coli . The recombinant N protein was migrated at 48 kDa and reacted with six histidine tag specific monoclonal antibody by immunoblotting . Recombinant N protein ELISA ( rnELISA ) demonstrated 98.7 % specificities among ( 80 ) PEDV-free individuals , and 98 % sensitivity ranging among ( 103 ) clinical samples with PEDV . On testing 884 field samples , an overall agreement of 88.3 % was generated between the SN and rnELISA . Taken together , these results indicated that nucleocapsid protein may be a useful antigen for the seradiagnosis of PEDV and it was also suggested that the ELISA is a highly sensitive and specific test for detecting antibodies to PEDV . #\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"An enzyme-linked immunosorbent assays ( ELISA ) based on recombinant nucleocapsid ( N ) protein generated in Escherichia coli was evaluated for its sensitivity and specificity for diagnosis of porcine epidemic diarrhea ( PEDV ) infection .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"The N gene encoding the N protein was cloned and expressed as a fusion protein with His tag protein in E. coli .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"The recombinant N protein was migrated at 48 kDa and reacted with six histidine tag specific monoclonal antibody by immunoblotting .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"Recombinant N protein ELISA ( rnELISA ) demonstrated 98.7 % specificities among ( 80 ) PEDV-free individuals ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"and 98 % sensitivity ranging among ( 103 ) clinical samples with PEDV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"On testing 884 field samples ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"an overall agreement of 88.3 % was generated between the SN and rnELISA .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"Taken together , these results indicated that nucleocapsid protein may be a useful antigen for the seradiagnosis of PEDV and it was also suggested that the ELISA is a highly sensitive and specific test for detecting antibodies to PEDV .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"#\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 9}]}"}]}
{"paper_id": "a7279f9dc72d858cc7f1c85a46c97c803eb47a69", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nRNAs are functionally diverse macromolecules whose proper functions rely strictly upon their correct tertiary structures . However , because of their high structural flexibility , correct folding of RNAs is challenging and slow . Therefore , cells and viruses encode a variety of RNA remodeling proteins , including helicases and RNA chaperones . In RNA viruses , these proteins are believed to play pivotal roles in all the processes involving viral RNAs during the life cycle . RNA helicases have been studied extensively for decades , whereas RNA chaperones , particularly virus-encoded RNA chaperones , are often overlooked . This review describes the activities of RNA chaperones encoded by RNA viruses , particularly the ones identified and characterized in recent years , and the functions of these proteins in different steps of viral life cycles , and presents an overview of this unique group of proteins .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"RNAs are functionally diverse macromolecules whose proper functions rely strictly upon their correct tertiary structures .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"However , because of their high structural flexibility ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"correct folding of RNAs is challenging and slow .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Therefore , cells and viruses encode a variety of RNA remodeling proteins ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"including helicases and RNA chaperones .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"In RNA viruses , these proteins are believed to play pivotal roles in all the processes involving viral RNAs during the life cycle .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"RNA helicases have been studied extensively for decades ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"whereas RNA chaperones , particularly virus-encoded RNA chaperones , are often overlooked .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"This review describes the activities of RNA chaperones encoded by RNA viruses ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}, {\"segment_text\": \"particularly the ones identified and characterized in recent years ,\", \"label\": \"purpose\", \"decision_reference\": \"boundary background_vs_purpose\", \"id\": 10}, {\"segment_text\": \"and the functions of these proteins in different steps of viral life cycles ,\", \"label\": \"purpose\", \"decision_reference\": \"boundary background_vs_purpose\", \"id\": 11}, {\"segment_text\": \"and presents an overview of this unique group of proteins .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 12}]}"}]}
{"paper_id": "e350e1b4aab99c73d0e0d03121b50c059c04fd61", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nA novel coronavirus ( SARS-CoV-2 ) is the causative agent of an emergent severe respiratory disease 20 in humans that is threatening to result in a global health crisis . By using genomic , sequence , 21 structural and evolutionary analysis , we show that Alpha-and Beta-CoVs possess several novel families 22 of immunoglobulin ( Ig ) domain proteins , including ORF8 and ORF7a from SARS-related coronaviruses 23 and two protein groups from certain Alpha-CoVs . Among them , ORF8 is distinguished in being rapidly 24 evolving , possessing a unique insert and a hypervariable position among SARS-CoV-2 genomes in its 25 predicted ligand-binding groove . We also uncover many Ig proteins from several metazoan viruses 26 which are distinct in sequence and structure but share an architecture comparable to that of CoV Ig 27 domain proteins . Hence , we propose that deployment of Ig domain proteins is a widely-used strategy by 28 viruses , and SARS-CoV-2 ORF8 is a potential pathogenicity factor which evolves rapidly to counter the 29 immune response and facilitate the transmission between hosts . 30 31\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"A novel coronavirus ( SARS-CoV-2 ) is the causative agent of an emergent severe respiratory disease 20 in humans that is threatening to result in a global health crisis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"By using genomic , sequence ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 2}, {\"segment_text\": \"21 structural and evolutionary analysis ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"we show that Alpha-and Beta-CoVs possess several novel families 22 of immunoglobulin ( Ig ) domain proteins ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"including ORF8 and ORF7a from SARS-related coronaviruses 23 and two protein groups from certain Alpha-CoVs .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"Among them , ORF8 is distinguished in being rapidly 24 evolving ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"possessing a unique insert and a hypervariable position among SARS-CoV-2 genomes in its 25 predicted ligand-binding groove .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"We also uncover many Ig proteins from several metazoan viruses 26 which are distinct in sequence and structure but share an architecture comparable to that of CoV Ig 27 domain proteins .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Hence , we propose that deployment of Ig domain proteins is a widely-used strategy by 28 viruses ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"and SARS-CoV-2 ORF8 is a potential pathogenicity factor which evolves rapidly to counter the 29 immune response and facilitate the transmission between hosts .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"30 31\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 11}]}"}]}
{"paper_id": "96041a41f60fce78d72972cd277cc5fd00dcf2f9", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nZika flavivirus infection during pregnancy appears to produce higher risk of microcephaly , and also causes multiple neurological problems such as Guillain-Barré syndrome . The Zika virus is now widespread in Central and South America , and is anticipated to become an increasing risk in the southern United States . With continuing global travel and the spread of the mosquito vector , the exposure is expected to accelerate , but there are no currently approved treatments against the Zika virus . The Zika NS2B/NS3 protease is an attractive drug target due to its essential role in viral replication . Our studies have identified several compounds with inhibitory activity ( IC 50 ) and binding affinity ( K D ) of ∼ 5-10 μM against the Zika NS2B-NS3 protease from testing 71 HCV NS3/NS4A inhibitors that were initially discovered by high-throughput screening of 40,967 compounds . Competition surface plasmon resonance studies and mechanism of inhibition analyses by enzyme kinetics subsequently determined the best compound to be a competitive inhibitor with a K i value of 9.5 μM . We also determined the X-ray structure of the Zika NS2B-NS3 protease in a `` pre-open conformation '' , a conformation never observed before for any flavivirus proteases . This provides the foundation for new structure-based inhibitor design . Zika flavivirus ; NS2B/NS3 serine protease ; Small molecule inhibitor ; apo ZIKV NS2B-NS3 pro structure Lee et al. .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Zika flavivirus infection during pregnancy appears to produce higher risk of microcephaly ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"and also causes multiple neurological problems such as Guillain-Barré syndrome .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"The Zika virus is now widespread in Central and South America ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"and is anticipated to become an increasing risk in the southern United States .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"With continuing global travel and the spread of the mosquito vector ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"the exposure is expected to accelerate ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"but there are no currently approved treatments against the Zika virus .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"The Zika NS2B/NS3 protease is an attractive drug target due to its essential role in viral replication .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 8}, {\"segment_text\": \"Our studies have identified several compounds with inhibitory activity ( IC 50 ) and binding affinity ( K D ) of ∼ 5-10 μM against the Zika NS2B-NS3 protease from testing 71 HCV NS3/NS4A inhibitors that were initially discovered by high-throughput screening of 40,967 compounds .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Competition surface plasmon resonance studies and mechanism of inhibition analyses by enzyme kinetics subsequently determined the best compound to be a competitive inhibitor with a K i value of 9.5 μM .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"We also determined the X-ray structure of the Zika NS2B-NS3 protease in a `` pre-open conformation '' ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"a conformation never observed before for any flavivirus proteases .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"This provides the foundation for new structure-based inhibitor design .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"Zika flavivirus ; NS2B/NS3 serine protease ; Small molecule inhibitor ; apo ZIKV NS2B-NS3 pro structure Lee et al. .\", \"label\": \"other\", \"decision_reference\": \"other.definition\", \"id\": 14}]}"}]}
{"paper_id": "ce1f762e478087400412172f30e184d92f17d976", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe individual and combined contribution of viral prevalence in the community to Emergency Department ( ED ) visits and hospitalizations with respiratory tract infections ( RTIs ) , chronic obstructive pulmonary disease ( COPD ) and asthma is unclear . Methods A retrospective analysis on daily viral positive tests and daily ED visits and hospitalizations between There were 4,365,578 ED visits with RTIs of which 321,719 ( 7.4 % ) were admitted to hospital ; 817,141 ED visits for COPD of which 260,665 ( 31.9 % ) were admitted and 649,666 ED visits with asthma of which 68,626 ( 10.6 % ) were admitted . The percentage of positive tests to influenza A and B , respiratory syncytial virus ( RSV ) , parainfluenza and adenovirus prevalence explained 57.4 % of ED visits and 63.8 % of hospitalizations for RTI , 41.4 % of ED visits and 39.2 % of hospitalizations with COPD but only 1.5 % of ED visits and 2.7 % of hospitalizations for asthma . The further addition of human metapneumovirus , rhinovirus and coronavirus over the final 3 years accounted for 66.7 % of ED visits and 74.4 % of hospitalizations for PLOS ONE | https://doi .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The individual and combined contribution of viral prevalence in the community to Emergency Department ( ED ) visits and hospitalizations with respiratory tract infections ( RTIs ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"chronic obstructive pulmonary disease ( COPD ) and asthma is unclear .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Methods\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 3}, {\"segment_text\": \"A retrospective analysis on daily viral positive tests and daily ED visits and hospitalizations between\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"There were 4,365,578 ED visits with RTIs of which 321,719 ( 7.4 % ) were admitted to hospital ; 817,141 ED visits for COPD of which 260,665 ( 31.9 % ) were admitted and 649,666 ED visits with asthma of which 68,626 ( 10.6 % ) were admitted .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"The percentage of positive tests to influenza A and B ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"respiratory syncytial virus ( RSV ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"parainfluenza and adenovirus prevalence explained 57.4 % of ED visits and 63.8 % of hospitalizations for RTI ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"41.4 % of ED visits and 39.2 % of hospitalizations with COPD but only 1.5 % of ED visits and 2.7 % of hospitalizations for asthma .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"The further addition of human metapneumovirus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"rhinovirus and coronavirus over the final 3 years accounted for 66.7 % of ED visits and 74.4 % of hospitalizations for PLOS ONE | https://doi .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}]}"}]}
{"paper_id": "604317acd27f5f663dc4be16155739c35e61ef24", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThis paper articulates the disproportionate policy perspective and uses it to mount four challenges for the new policy design orientation . First , in contrast to the new policy design thinking , disproportionate policy options may be systematically designed , and at times , successfully implemented . Second , in contrast to the new policy design thinking , there are certain conditions under which policymakers may tend to develop effective response , with cost considerations becoming only secondary in importance if at all ( read , policy overreaction ) , or cost-conscious response , with effectiveness considerations becoming only secondary in importance if at all ( read , policy underreaction ) . Third , in contrast to the new policy design thinking , disproportionate policy options may be designed for purposes other than implementation ( e.g. , to be used as signaling devices or as context-setters ) . Fourth , in contrast to new policy design thinking , there are certain conditions under which the emotional arena of policy may be equally , if not more , important than the substantive one . The paper concludes that so far the literature on new policy design has not responded to the emergence of the disproportionate policy perspective , but a robust research agenda awaits those answering this paper 's call for action .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"This paper articulates the disproportionate policy perspective and uses it to mount four challenges for the new policy design orientation .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"First , in contrast to the new policy design thinking ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 2}, {\"segment_text\": \"disproportionate policy options may be systematically designed ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 3}, {\"segment_text\": \"and at times , successfully implemented .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Second , in contrast to the new policy design thinking ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"there are certain conditions under which policymakers may tend to develop effective response ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"with cost considerations becoming only secondary in importance if at all ( read , policy overreaction ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"or cost-conscious response , with effectiveness considerations becoming only secondary in importance if at all ( read , policy underreaction ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Third , in contrast to the new policy design thinking ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"disproportionate policy options may be designed for purposes other than implementation ( e.g. , to be used as signaling devices or as context-setters ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"Fourth , in contrast to new policy design thinking ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"there are certain conditions under which the emotional arena of policy may be equally ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"if not more , important than the substantive one .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"The paper concludes that so far the literature on new policy design has not responded to the emergence of the disproportionate policy perspective ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"but a robust research agenda awaits those answering this paper 's call for action .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}]}"}]}
{"paper_id": "765f07ace8a0cf6dd8c3404ade733123a9a1450d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nStreptococcus equi subsp. zooepidemicus has been linked to cases of acute fatal pneumonia in dogs in several countries . Outbreaks can occur in kenneled dog populations and result in significant levels of morbidity and mortality . This highly contagious disease is characterized by the sudden onset of clinical signs , including pyrexia , dyspnea , and hemorrhagic nasal discharge . The pathogenesis of S. equi subsp. zooepidemicus infection in dogs is poorly understood . This study systematically characterized the histopathological changes in the lungs of 39 dogs from a large rehoming shelter in London , United Kingdom ; the dogs were infected with S. equi subsp. zooepidemicus . An objective scoring system demonstrated that S. equi subsp. zooepidemicus caused pneumonia in 26/39 ( 66.7 % ) dogs , and most of these dogs ( 17/26 ( 65.4 % ) ) were classified as severe fibrinosuppurative , necrotizing , and hemorrhagic . Three recently described superantigen genes ( szeF , szeN , and szeP ) were detected by PCR in 17/47 ( 36.2 % ) of the S. equi subsp. zooepidemicus isolates ; however , there was no association between the presence of these genes and the histopathological score . The lungs of S. equi subsp. . zooepidemicus-infected dogs with severe respiratory signs and lung pathology did however have significantly higher mRNA levels of the proinflammatory cytokines tumor necrosis factor alpha ( TNF - ␣ ) , interleukin 6 ( IL-6 ) , and interleukin 8 ( IL-8 ) than in uninfected controls , suggesting a role for an exuberant host immune response in the pathogenesis of this disease .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Streptococcus equi subsp. zooepidemicus has been linked to cases of acute fatal pneumonia in dogs in several countries .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Outbreaks can occur in kenneled dog populations and result in significant levels of morbidity and mortality .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"This highly contagious disease is characterized by the sudden onset of clinical signs ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"including pyrexia , dyspnea , and hemorrhagic nasal discharge .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"The pathogenesis of S. equi subsp. zooepidemicus infection in dogs is poorly understood .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"This study systematically characterized the histopathological changes in the lungs of 39 dogs from a large rehoming shelter in London ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"United Kingdom ; the dogs were infected with S. equi subsp. zooepidemicus .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 7}, {\"segment_text\": \"An objective scoring system demonstrated that S. equi subsp. zooepidemicus caused pneumonia in 26/39 ( 66.7 % ) dogs ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 8}, {\"segment_text\": \"and most of these dogs ( 17/26 ( 65.4 % ) ) were classified as severe fibrinosuppurative , necrotizing , and hemorrhagic .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 9}, {\"segment_text\": \"Three recently described superantigen genes ( szeF , szeN , and szeP ) were detected by PCR in 17/47 ( 36.2 % ) of the S. equi subsp. zooepidemicus isolates ; however ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"there was no association between the presence of these genes and the histopathological score .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"The lungs of S. equi subsp. .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"zooepidemicus-infected dogs with severe respiratory signs and lung pathology did however have significantly higher mRNA levels of the proinflammatory cytokines tumor necrosis factor alpha ( TNF - ␣ ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"interleukin 6 ( IL-6 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"and interleukin 8 ( IL-8 ) than in uninfected controls ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"suggesting a role for an exuberant host immune response in the pathogenesis of this disease .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}]}"}]}
{"paper_id": "c6e292ee5d1b36c7b254bd2302b9fc2cf2190b0d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground Ethnic minorities in Europe such as the Chinese may need a special strategy with regard to risk communication about emerging infectious diseases . To engage them in precautionary actions , it is important to know their information sources , knowledge , and health beliefs . Purpose This study 's purpose is to study the use of information sources , knowledge , and health beliefs related to SARS and avian flu of Chinese people in the UK and The Netherlands , and to make comparisons with the general population in these countries . Method Results of a self-administered questionnaire among 300 British/Dutch Chinese were compared to data obtained from a computer-assisted phone survey among the general population ( n = 800 ) . Results British/Dutch Chinese got most information about emerging diseases from family and friends , followed by Chinese media and British/Dutch TV . They had less confidence than general groups in their doctor , government agencies , and consumer/patient interest groups . Their knowledge of SARS was high . They had a lower perceived threat than general populations with regard to SARS and avian flu due to a lower perceived severity . They had higher selfefficacy beliefs regarding SARS and avian flu . Conclusion In case of new outbreaks of SARS/avian flu in China , local authorities in the UK and The Netherlands can best reach Chinese people through informal networks and British/Dutch TV , while trying to improve confidence in information from the government . In communications , the severity of the disease rather than the susceptibility appears to need most attention .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background Ethnic minorities in Europe such as the Chinese may need a special strategy with regard to risk communication about emerging infectious diseases .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"To engage them in precautionary actions ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"it is important to know their information sources ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"knowledge , and health beliefs .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Purpose This study 's purpose is to study the use of information sources ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"knowledge , and health beliefs related to SARS and avian flu of Chinese people in the UK and The Netherlands ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"and to make comparisons with the general population in these countries .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"Method Results of a self-administered questionnaire among 300 British/Dutch Chinese were compared to data obtained from a computer-assisted phone survey among the general population ( n = 800 ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Results British/Dutch Chinese got most information about emerging diseases from family and friends ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"followed by Chinese media and British/Dutch TV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"They had less confidence than general groups in their doctor ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"government agencies , and consumer/patient interest groups .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Their knowledge of SARS was high .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"They had a lower perceived threat than general populations with regard to SARS and avian flu due to a lower perceived severity .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"They had higher selfefficacy beliefs regarding SARS and avian flu .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"Conclusion In case of new outbreaks of SARS/avian flu in China ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"local authorities in the UK and The Netherlands can best reach Chinese people through informal networks and British/Dutch TV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"while trying to improve confidence in information from the government .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"In communications , the severity of the disease rather than the susceptibility appears to need most attention .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}]}"}]}
{"paper_id": "08a3e8af143f9b97a9ba5220f0de0fe0ae1bba06", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nVirus infection initiates a number of cellular stress responses that modulate gene regulation and compartmentalization of RNA . Viruses must control host gene expression and the localization of viral RNAs to be successful parasites . RNA granules such as stress granules and P-bodies contain translationally silenced messenger ribonucleoproteins ( mRNPs ) and serve as extensions of translation regulation in cells , storing transiently repressed mRNAs . New reports show a growing number of virus families modulate RNA granule function to maximize replication efficiency . This review summarizes recent advances in understanding the relationship between viruses and mRNA stress granules in animal cells and will discuss important questions that remain in this emerging field .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Virus infection initiates a number of cellular stress responses that modulate gene regulation and compartmentalization of RNA .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"Viruses must control host gene expression and the localization of viral RNAs to be successful parasites .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"RNA granules such as stress granules and P-bodies contain translationally silenced messenger ribonucleoproteins ( mRNPs ) and serve as extensions of translation regulation in cells , storing transiently repressed mRNAs .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"New reports show a growing number of virus families modulate RNA granule function to maximize replication efficiency .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"This review summarizes recent advances in understanding the relationship between viruses and mRNA stress granules in animal cells and will discuss important questions that remain in this emerging field .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}]}"}]}
{"paper_id": "ffdd6ba963bcbed1b9e7a293b06529bb4da989b6", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nComparing sequences of archived viruses collected over many years to the present allows the study of viral evolution and contributes to the design of new vaccines . However , the difficulty , time and expense of generating full-length sequences individually from each archived sample have hampered these studies . Next generation sequencing technologies have been utilized for analysis of clinical and environmental samples to identify viral pathogens that may be present . This has led to the discovery of many new , uncharacterized viruses from a number of viral families . Use of these sequencing technologies would be advantageous in examining viral evolution . In this study , a sequencing procedure was used to sequence simultaneously and rapidly multiple archived samples using a single standard protocol . This procedure utilized primers composed of 20 bases of known sequence with 8 random bases at the 3 - end that also served as an identifying barcode that allowed the differentiation each viral library following pooling and sequencing . This conferred sequence independence by random priming both first and second strand cDNA synthesis . Viral stocks were treated with a nuclease cocktail to reduce the presence of host nucleic acids . Viral RNA was extracted , followed by single tube random-primed double-stranded cDNA synthesis . The resultant cDNAs were amplified by primer-specific PCR , pooled , size fractionated and sequenced on the Ion Torrent PGM platform . The individual virus genomes were readily assembled by both de novo and template-assisted assembly methods . This procedure consistently resulted in near full length , if not full-length , genomic sequences and was used to sequence multiple bovine pestivirus and coronavirus isolates simultaneously . Published by Elsevier B.V.\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Comparing sequences of archived viruses collected over many years to the present allows the study of viral evolution and contributes to the design of new vaccines .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"However , the difficulty , time and expense of generating full-length sequences individually from each archived sample have hampered these studies .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Next generation sequencing technologies have been utilized for analysis of clinical and environmental samples to identify viral pathogens that may be present .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"This has led to the discovery of many new ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"uncharacterized viruses from a number of viral families .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"Use of these sequencing technologies would be advantageous in examining viral evolution .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"In this study , a sequencing procedure was used to sequence simultaneously and rapidly multiple archived samples using a single standard protocol .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"This procedure utilized primers composed of 20 bases of known sequence with 8 random bases at the 3 - end that also served as an identifying barcode that allowed the differentiation each viral library following pooling and sequencing .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"This conferred sequence independence by random priming both first and second strand cDNA synthesis .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Viral stocks were treated with a nuclease cocktail to reduce the presence of host nucleic acids .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Viral RNA was extracted , followed by single tube random-primed double-stranded cDNA synthesis .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 11}, {\"segment_text\": \"The resultant cDNAs were amplified by primer-specific PCR ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"pooled , size fractionated and sequenced on the Ion Torrent PGM platform .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"The individual virus genomes were readily assembled by both de novo and template-assisted assembly methods .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 14}, {\"segment_text\": \"This procedure consistently resulted in near full length ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"if not full-length , genomic sequences and was used to sequence multiple bovine pestivirus and coronavirus isolates simultaneously .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"Published by Elsevier B.V.\", \"label\": \"other\", \"decision_reference\": \"other.rule\", \"id\": 17}]}"}]}
{"paper_id": "deeacb8558e3403c69cd8db9f4e8e5214fd85c46", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Mammalian angiotensin converting enzyme ( ACE ) plays a key role in blood pressure regulation . Although multiple ACE-like proteins exist in non-mammalian organisms , to date only one other ACE homologue , ACE2 , has been identified in mammals . Here we report the identification and characterisation of the gene encoding a third homologue of ACE , termed ACE3 , in several mammalian genomes . The ACE3 gene is located on the same chromosome downstream of the ACE gene . Multiple sequence alignment and molecular modelling have been employed to characterise the predicted ACE3 protein . In mouse , rat , cow and dog , the predicted protein has mutations in some of the critical residues involved in catalysis , including the catalytic Glu in the HEXXH zinc binding motif which is Gln , and ESTs or reversetranscription PCR indicate that the gene is expressed . In humans , the predicted ACE3 protein has an intact HEXXH motif , but there are other deletions and insertions in the gene and no ESTs have been identified . In the genomes of several mammalian species there is a gene that encodes a novel , single domain ACE-like protein , ACE3 . In mouse , rat , cow and dog ACE3 , the catalytic Glu is replaced by Gln in the putative zinc binding motif , indicating that in these species ACE3 would lack catalytic activity as a zinc metalloprotease . In humans , no evidence was found that the ACE3 gene is expressed and the presence of deletions and insertions in the sequence indicate that ACE3 is a pseudogene .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Mammalian angiotensin converting enzyme ( ACE ) plays a key role in blood pressure regulation .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Although multiple ACE-like proteins exist in non-mammalian organisms ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"to date only one other ACE homologue ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"ACE2 , has been identified in mammals .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"Here we report the identification and characterisation of the gene encoding a third homologue of ACE ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 5}, {\"segment_text\": \"termed ACE3 , in several mammalian genomes .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 6}, {\"segment_text\": \"The ACE3 gene is located on the same chromosome downstream of the ACE gene .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"Multiple sequence alignment and molecular modelling have been employed to characterise the predicted ACE3 protein .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"In mouse , rat , cow and dog ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"the predicted protein has mutations in some of the critical residues involved in catalysis ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"including the catalytic Glu in the HEXXH zinc binding motif which is Gln ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"and ESTs or reversetranscription PCR indicate that the gene is expressed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"In humans , the predicted ACE3 protein has an intact HEXXH motif ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"but there are other deletions and insertions in the gene and no ESTs have been identified .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"In the genomes of several mammalian species there is a gene that encodes a novel ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"single domain ACE-like protein , ACE3 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"In mouse , rat , cow and dog ACE3 ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"the catalytic Glu is replaced by Gln in the putative zinc binding motif ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"indicating that in these species ACE3 would lack catalytic activity as a zinc metalloprotease .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"In humans , no evidence was found that the ACE3 gene is expressed and the presence of deletions and insertions in the sequence indicate that ACE3 is a pseudogene .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}]}"}]}
{"paper_id": "c05b1349d118b8d75eb1e86d5d31132d5f3fb186", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nFollowing the outbreak of novel Severe Acute Respiratory Syndrome Coronavirus-2 ( SARS-CoV-2 ) or COVID-19 in Wuhan , China late 2019 , different countries have put in place interventions such as travel ban , proper hygiene , and social distancing to slow the spread of this novel virus . We evaluated the effects of travel bans in the Australia context and projected the epidemic until May 2020 . Our modelling results closely align with observed cases in Australia indicating the need for maintaining or improving on the control measures to slow down the virus .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Following the outbreak of novel Severe Acute Respiratory Syndrome Coronavirus-2 ( SARS-CoV-2 ) or COVID-19 in Wuhan ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"China late 2019 , different countries have put in place interventions such as travel ban ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"proper hygiene , and social distancing to slow the spread of this novel virus .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"We evaluated the effects of travel bans in the Australia context and projected the epidemic until May 2020 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"Our modelling results closely align with observed cases in Australia indicating the need for maintaining or improving on the control measures to slow down the virus .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}]}"}]}
{"paper_id": "650c105dc3718ea36a7abffa0de7f9068390045f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe innate immune response provides the first line of defense against viruses and other pathogens by responding to specific microbial molecules . Influenza A virus ( IAV ) produces double-stranded RNA as an intermediate during the replication life cycle , which activates the intracellular pathogen recognition receptor RIG-I and induces the production of proinflammatory cytokines and antiviral interferon . Understanding the mechanisms that regulate innate immune responses to IAV and other viruses is of key importance to develop novel therapeutic strategies . Here we used myeloid cell specific A20 knockout mice to examine the role of the ubiquitin-editing protein A20 in the response of myeloid cells to IAV infection . A20 deficient macrophages were hyperresponsive to double stranded RNA and IAV infection , as illustrated by enhanced NF-kB and IRF3 activation , concomitant with increased production of proinflammatory cytokines , chemokines and type I interferon . In vivo this was associated with an increased number of alveolar macrophages and neutrophils in the lungs of IAV infected mice . Surprisingly , myeloid cell specific A20 knockout mice are protected against lethal IAV infection . These results challenge the general belief that an excessive host proinflammatory response is associated with IAV-induced lethality , and suggest that under certain conditions inhibition of A20 might be of interest in the management of IAV infections .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The innate immune response provides the first line of defense against viruses and other pathogens by responding to specific microbial molecules .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Influenza A virus ( IAV ) produces double-stranded RNA as an intermediate during the replication life cycle ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"which activates the intracellular pathogen recognition receptor RIG-I and induces the production of proinflammatory cytokines and antiviral interferon .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Understanding the mechanisms that regulate innate immune responses to IAV and other viruses is of key importance to develop novel therapeutic strategies .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"Here we used myeloid cell specific A20 knockout mice to examine the role of the ubiquitin-editing protein A20 in the response of myeloid cells to IAV infection .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"A20 deficient macrophages were hyperresponsive to double stranded RNA and IAV infection ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"as illustrated by enhanced NF-kB and IRF3 activation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 7}, {\"segment_text\": \"concomitant with increased production of proinflammatory cytokines ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 8}, {\"segment_text\": \"chemokines and type I interferon .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"In vivo this was associated with an increased number of alveolar macrophages and neutrophils in the lungs of IAV infected mice .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"Surprisingly , myeloid cell specific A20 knockout mice are protected against lethal IAV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"These results challenge the general belief that an excessive host proinflammatory response is associated with IAV-induced lethality ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"and suggest that under certain conditions inhibition of A20 might be of interest in the management of IAV infections .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}]}"}]}
{"paper_id": "d57066fb6b0be503b07e3d19f20166d06af60b18", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe RNA-dependent RNA polymerases ( RdRPs ) encoded by the RNA viruses are a unique class of nucleic acid polymerases . Each viral RdRP contains a 500-600 residue catalytic module with palm , fingers , and thumb domains forming an encircled human right hand architecture . Seven polymerase catalytic motifs are located in the RdRP palm and fingers domains , comprising the most conserved parts of the RdRP and are responsible for the RNA-only specificity in catalysis . Functional regions are often found fused to the RdRP catalytic module , resulting in a high level of diversity in RdRP global structure and regulatory mechanism . In this review , we surveyed all 46 RdRP-sequence available virus families of the positive-strand RNA viruses listed in the 2018b collection of the International Committee on Virus Taxonomy ( ICTV ) and chose a total of 49 RdRPs as representatives . By locating hallmark residues in RdRP catalytic motifs and by referencing structural and functional information in the literature , we were able to estimate the N-and C-terminal boundaries of the catalytic module in these RdRPs , which in turn serve as reference points to predict additional functional regions beyond the catalytic module . Interestingly , a large number of virus families may have additional regions fused to the RdRP N-terminus , while only a few of them have such regions on the C-terminal side of the RdRP . The current knowledge on these additional regions , either in three-dimensional ( 3D ) structure or in function , is quite limited . In the five RdRP-structure available virus families in the positive-strand RNA viruses , only the Flaviviridae family has the 3D structural information resolved for such regions . Hence , future efforts to solve full-length RdRP structures containing these regions and to dissect the functional contribution of them are necessary to improve the overall understanding of the RdRP proteins as an evolutionarily integrated group , and our analyses here may serve as a guideline for selecting representative RdRP systems in these studies .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The RNA-dependent RNA polymerases ( RdRPs ) encoded by the RNA viruses are a unique class of nucleic acid polymerases .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"Each viral RdRP contains a 500-600 residue catalytic module with palm ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"fingers , and thumb domains forming an encircled human right hand architecture .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Seven polymerase catalytic motifs are located in the RdRP palm and fingers domains ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"comprising the most conserved parts of the RdRP and are responsible for the RNA-only specificity in catalysis .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"Functional regions are often found fused to the RdRP catalytic module ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"resulting in a high level of diversity in RdRP global structure and regulatory mechanism .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"In this review , we surveyed all 46 RdRP-sequence available virus families of the positive-strand RNA viruses listed in the 2018b collection of the International Committee on Virus Taxonomy ( ICTV ) and chose a total of 49 RdRPs as representatives .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"By locating hallmark residues in RdRP catalytic motifs and by referencing structural and functional information in the literature ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"we were able to estimate the N-and C-terminal boundaries of the catalytic module in these RdRPs ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"which in turn serve as reference points to predict additional functional regions beyond the catalytic module .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"Interestingly , a large number of virus families may have additional regions fused to the RdRP N-terminus ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"while only a few of them have such regions on the C-terminal side of the RdRP .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"The current knowledge on these additional regions ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"either in three-dimensional ( 3D ) structure or in function , is quite limited .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"In the five RdRP-structure available virus families in the positive-strand RNA viruses ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"only the Flaviviridae family has the 3D structural information resolved for such regions .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"Hence , future efforts to solve full-length RdRP structures containing these regions and to dissect the functional contribution of them are necessary to improve the overall understanding of the RdRP proteins as an evolutionarily integrated group ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"and our analyses here may serve as a guideline for selecting representative RdRP systems in these studies .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}]}"}]}
{"paper_id": "8cfec61753b072e72aa52b6c48a77e68133b3f18", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nOne sentence summary : This review summarizes recent discoveries on the genetic and phenotypic traits required for airborne transmission of zoonotic influenza viruses of subtypes H5 , H7 and H9 and pandemic viruses of subtypes H1 , H2 and H3 . Many respiratory viruses of humans originate from animals . For instance , there are now eight paramyxoviruses , four coronaviruses and four orthomxoviruses that cause recurrent epidemics in humans but were once confined to other hosts . In the last decade , several members of the same virus families have jumped the species barrier from animals to humans . Fortunately , these viruses have not become established in humans , because they lacked the ability of sustained transmission between humans . However , these outbreaks highlighted the lack of understanding of what makes a virus transmissible . In part triggered by the relatively high frequency of occurrence of influenza A virus zoonoses and pandemics , the influenza research community has started to investigate the viral genetic and biological traits that drive virus transmission via aerosols or respiratory droplets between mammals . Here we summarize recent discoveries on the genetic and phenotypic traits required for airborne transmission of zoonotic influenza viruses of subtypes H5 , H7 and H9 and pandemic viruses of subtypes H1 , H2 and H3 . Increased understanding of the determinants and mechanisms of respiratory virus transmission is not only key from a basic scientific perspective , but may also aid in assessing the risks posed by zoonotic viruses to human health , and preparedness for such risks .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"One sentence summary : This review summarizes recent discoveries on the genetic and phenotypic traits required for airborne transmission of zoonotic influenza viruses of subtypes H5 ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"H7 and H9 and pandemic viruses of subtypes H1 , H2 and H3 .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"Many respiratory viruses of humans originate from animals .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"For instance , there are now eight paramyxoviruses ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"four coronaviruses and four orthomxoviruses that cause recurrent epidemics in humans but were once confined to other hosts .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"In the last decade , several members of the same virus families have jumped the species barrier from animals to humans .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 6}, {\"segment_text\": \"Fortunately , these viruses have not become established in humans ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 7}, {\"segment_text\": \"because they lacked the ability of sustained transmission between humans .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 8}, {\"segment_text\": \"However , these outbreaks highlighted the lack of understanding of what makes a virus transmissible .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 9}, {\"segment_text\": \"In part triggered by the relatively high frequency of occurrence of influenza A virus zoonoses and pandemics ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 10}, {\"segment_text\": \"the influenza research community has started to investigate the viral genetic and biological traits that drive virus transmission via aerosols or respiratory droplets between mammals .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 11}, {\"segment_text\": \"Here we summarize recent discoveries on the genetic and phenotypic traits required for airborne transmission of zoonotic influenza viruses of subtypes H5 ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 12}, {\"segment_text\": \"H7 and H9 and pandemic viruses of subtypes H1 , H2 and H3 .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 13}, {\"segment_text\": \"Increased understanding of the determinants and mechanisms of respiratory virus transmission is not only key from a basic scientific perspective ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"but may also aid in assessing the risks posed by zoonotic viruses to human health ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"and preparedness for such risks .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}]}"}]}
{"paper_id": "4598e96f24115b1fd9bc0247cdd88e52beb5268f", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nCD13/Aminopeptidase N ( CD13 ) is known to play an important role in tumour cell invasion . We examined whether basic fibroblast growth factor ( bFGF ) is involved in the regulation of CD13 expression in human melanoma cells . 1F6 human melanoma cells were stably transfected with constructs encoding either the 18 kDa ( 18kD ) or all ( ALL ) bFGF isoform proteins . We observed highly increased CD13 mRNA and protein expression in the 1F6 clones regardless of the overexpression of either the 18kD or all isoform proteins . Neutral aminopeptidase activity was increased five-fold and could be inhibited by bestatin and the CD13-neutralising antibody WM15 . The enhanced invasion through Matrigel , but not migration in a wound assay , was efficiently abrogated by both bestatin and WM15 . Upregulation of CD13 expression was the result of increased epithelial and myeloid promoter activity up to 4.5 fold in 1F6-18kD and 1F6-ALL clones . Interestingly , in a panel of human melanoma cell lines , a significant correlation ( r 2 1/4 0.883 , Po0 .05 ) between bFGF and CD13 mRNA and protein expression was detected . High bFGF and CD13 expression were clearly related with an aggressive phenotype . Taken together , our data indicate that high bFGF expression upregulates CD13 expression in human melanoma cells by activating both the myeloid and the epithelial CD13 promoter . In addition , we show that high bFGF and CD13 expression results in enhanced invasive capacity and metastatic behaviour of human melanoma cells .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"CD13/Aminopeptidase N ( CD13 ) is known to play an important role in tumour cell invasion .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"We examined whether basic fibroblast growth factor ( bFGF ) is involved in the regulation of CD13 expression in human melanoma cells .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"1F6 human melanoma cells were stably transfected with constructs encoding either the 18 kDa ( 18kD ) or all ( ALL ) bFGF isoform proteins .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"We observed highly increased CD13 mRNA and protein expression in the 1F6 clones regardless of the overexpression of either the 18kD or all isoform proteins .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 4}, {\"segment_text\": \"Neutral aminopeptidase activity was increased five-fold and could be inhibited by bestatin and the CD13-neutralising antibody WM15 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 5}, {\"segment_text\": \"The enhanced invasion through Matrigel ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 6}, {\"segment_text\": \"but not migration in a wound assay ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"was efficiently abrogated by both bestatin and WM15 .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Upregulation of CD13 expression was the result of increased epithelial and myeloid promoter activity up to 4.5 fold in 1F6-18kD and 1F6-ALL clones .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Interestingly , in a panel of human melanoma cell lines ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"a significant correlation ( r 2 1/4 0.883 , Po0 .05 ) between bFGF and CD13 mRNA and protein expression was detected .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"High bFGF and CD13 expression were clearly related with an aggressive phenotype .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"Taken together , our data indicate that high bFGF expression upregulates CD13 expression in human melanoma cells by activating both the myeloid and the epithelial CD13 promoter .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"In addition , we show that high bFGF and CD13 expression results in enhanced invasive capacity and metastatic behaviour of human melanoma cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}]}"}]}
{"paper_id": "d4b76917de146cdbe4c922c15ac3d87d3d483446", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Feline Infectious Peritonitis ( FIP ) is a lethal systemic disease , caused by the FIP Virus ( FIPV ) ; a virulent mutant of Feline Enteric Coronavirus ( FECV ) . Currently , the viruses virulence determinants and host gene expressions during FIPV infection are not fully understood . Methods : RNA sequencing of Crandell Rees Feline Kidney ( CRFK ) cells , infected with FIPV strain 79-1146 at 3 hours post infection ( h.p.i ) , were sequenced using the Illumina next generation sequencing approach . Bioinformatic 's analysis , based on Felis catus 2X annotated shotgun reference genome , using CLC bio Genome Workbench mapped both control and infected cell reads to 18899 genes out of 19046 annotated genes . Kal 's Z test statistical analysis was used to analyse the differentially expressed genes from the infected CRFK cells . Real time RT-qPCR was developed for further transcriptional profiling of three genes ( PD-1 , PD-L1 and A3H ) in infected CRFK cells and Peripheral Blood Mononuclear Cells ( PBMCs ) from healthy and FIP-diseased cats . Results : Based on Kal 's Z-test , with False Discovery Rate ( FDR ) < 0.05 and > 1.99 fold change on gene expressions , a total of 61 genes were differentially expressed by both samples , where 44 genes were up-regulated and the remainder were down-regulated . Most genes were closely clustered together , suggesting a homogeneous expression . The majority of the genes that were significantly regulated , were those associated with monocytes-macrophage and Th1 cell functions , and the regulation of apoptosis . Real time RT-qPCR developed focusing on 2 up-regulated genes ( PD-L1 and A3H ) together with an apoptosis associated gene PD-1 expressions in FIPV infected CRFK cells and in PBMCs from healthy and FIP diagnosed cats produced concordant results with transcriptome data . Conclusion : The possible roles of these genes , and their importance in feline coronaviruses infection , are discussed .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Feline Infectious Peritonitis ( FIP ) is a lethal systemic disease ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"caused by the FIP Virus ( FIPV ) ; a virulent mutant of Feline Enteric Coronavirus ( FECV ) .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"Currently , the viruses virulence determinants and host gene expressions during FIPV infection are not fully understood .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 3}, {\"segment_text\": \"Methods : RNA sequencing of Crandell Rees Feline Kidney ( CRFK ) cells ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 4}, {\"segment_text\": \"infected with FIPV strain 79-1146 at 3 hours post infection ( h.p.i ) ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"were sequenced using the Illumina next generation sequencing approach .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"Bioinformatic 's analysis , based on Felis catus 2X annotated shotgun reference genome ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"using CLC bio Genome Workbench mapped both control and infected cell reads to 18899 genes out of 19046 annotated genes .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Kal 's Z test statistical analysis was used to analyse the differentially expressed genes from the infected CRFK cells .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 9}, {\"segment_text\": \"Real time RT-qPCR was developed for further transcriptional profiling of three genes ( PD-1 , PD-L1 and A3H ) in infected CRFK cells and Peripheral Blood Mononuclear Cells ( PBMCs ) from healthy and FIP-diseased cats .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 10}, {\"segment_text\": \"Results : Based on Kal 's Z-test ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"with False Discovery Rate ( FDR ) < 0.05 and > 1.99 fold change on gene expressions ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"a total of 61 genes were differentially expressed by both samples ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"where 44 genes were up-regulated and the remainder were down-regulated .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"Most genes were closely clustered together , suggesting a homogeneous expression .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"The majority of the genes that were significantly regulated ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"were those associated with monocytes-macrophage and Th1 cell functions ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}, {\"segment_text\": \"and the regulation of apoptosis .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 18}, {\"segment_text\": \"Real time RT-qPCR developed focusing on 2 up-regulated genes ( PD-L1 and A3H ) together with an apoptosis associated gene PD-1 expressions in FIPV infected CRFK cells and in PBMCs from healthy and FIP diagnosed cats produced concordant results with transcriptome data .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"Conclusion : The possible roles of these genes ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"and their importance in feline coronaviruses infection , are discussed .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}]}"}]}
{"paper_id": "8e9ea0dac7420cfa7ed81e2783f38896ba865196", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nThe vast majority of the more than 1 billion doses of vaccines manufactured worldwide each year are given to perfectly healthy people . 1-4 It is this fact that drives the requirements for vaccines to be among the most rigorously designed , monitored , and compliant products manufactured today . The ability to manufacture these vaccines safely and consistently is built on four competencies :\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"The vast majority of the more than 1 billion doses of vaccines manufactured worldwide each year are given to perfectly healthy people .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"1-4 It is this fact that drives the requirements for vaccines to be among the most rigorously designed ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"monitored , and compliant products manufactured today .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"The ability to manufacture these vaccines safely and consistently is built on four competencies :\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 4}]}"}]}
{"paper_id": "2089844227bd2ff234044e4b311bf1c2bcb3838c", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nBackground : Respiratory virome is an integral part of the human microbiome and its characterization may contribute to a better understanding of the changes that arise in the disease and , consequently , influence the approach and treatment of patients with acute lower respiratory infections . The aim of this study was to evaluate the presence of respiratory viruses in the lower airways of individuals undergoing invasive mechanical ventilation , with and without acute lower respiratory infection ( respectively WRI and WORI groups ) . Methods : We studied 44 mini-bronchoalveolar lavage samples ( collected with a double catheter , Combicath ® kit ) from patients with mean age in the seventh decade , 20 from WORI group and 24 from WRI group , who were hospitalized for acute respiratory failure in Intensive Care Units of two hospitals in the Lisbon area . Real-time PCR was applied to verify analyse the presence of 15 common respiratory viruses ( adenovirus , human bocavirus , influenza virus A and B , repiratory syncytial virus , human parainfluenza virus types 1 , 2 , 3 and 4 , human enterovirus , human rhinovirus , human metapneumovirus , human coronavirus group 1 ( 229E , NL63 ) and 2 ( OC43 , HKU1 ) . Results : Respiratory viruses were detected in six of the 20 patients in the WORI group : influenza AH3 ( n = 2 ) , parainfluenza virus 1/3 ( n = 2 ) , human rhinovirus ( n = 2 ) , respiratory syncytial virus ( n = 1 ) and human metapneumovirus ( n = 1 ) . In the WRI group , respiratory viruses were detected in 12 of the 24 patients : influenza AH3 ( n = 3 ) , human rhinovirus ( n = 3 ) , respiratory syncytial virus ( n = 3 ) , human metapneumovirus ( n = 3 ) , human bocavirus ( n = 2 ) and human enterovirus ( n = 1 ) . Simultaneous detection of two viruses was recorded in two samples in both groups . Conclusions : The results of this study suggest the presence of common respiratory viruses in the lower respiratory tract without causing symptomatic infection , even in carefully collected lower samples . This may have important implications on the interpretation of the results on the diagnostic setting .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Background : Respiratory virome is an integral part of the human microbiome and its characterization may contribute to a better understanding of the changes that arise in the disease and ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"consequently , influence the approach and treatment of patients with acute lower respiratory infections .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"The aim of this study was to evaluate the presence of respiratory viruses in the lower airways of individuals undergoing invasive mechanical ventilation ,\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 3}, {\"segment_text\": \"with and without acute lower respiratory infection ( respectively WRI and WORI groups ) .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 4}, {\"segment_text\": \"Methods : We studied 44 mini-bronchoalveolar lavage samples ( collected with a double catheter , Combicath ® kit ) from patients with mean age in the seventh decade ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 5}, {\"segment_text\": \"20 from WORI group and 24 from WRI group ,\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 6}, {\"segment_text\": \"who were hospitalized for acute respiratory failure in Intensive Care Units of two hospitals in the Lisbon area .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 7}, {\"segment_text\": \"Real-time PCR was applied to verify analyse the presence of 15 common respiratory viruses ( adenovirus , human bocavirus , influenza virus A and B , repiratory syncytial virus , human parainfluenza virus types 1 , 2 , 3 and 4 , human enterovirus , human rhinovirus , human metapneumovirus , human coronavirus group 1 ( 229E , NL63 ) and 2 ( OC43 , HKU1 ) .\", \"label\": \"method\", \"decision_reference\": \"method.rule\", \"id\": 8}, {\"segment_text\": \"Results : Respiratory viruses were detected in six of the 20 patients in the WORI group : influenza AH3 ( n = 2 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 9}, {\"segment_text\": \"parainfluenza virus 1/3 ( n = 2 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"human rhinovirus ( n = 2 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"respiratory syncytial virus ( n = 1 ) and human metapneumovirus ( n = 1 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 12}, {\"segment_text\": \"In the WRI group , respiratory viruses were detected in 12 of the 24 patients : influenza AH3 ( n = 3 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"human rhinovirus ( n = 3 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}, {\"segment_text\": \"respiratory syncytial virus ( n = 3 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 15}, {\"segment_text\": \"human metapneumovirus ( n = 3 ) ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 16}, {\"segment_text\": \"human bocavirus ( n = 2 ) and human enterovirus ( n = 1 ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 17}, {\"segment_text\": \"Simultaneous detection of two viruses was recorded in two samples in both groups .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 18}, {\"segment_text\": \"Conclusions : The results of this study suggest the presence of common respiratory viruses in the lower respiratory tract without causing symptomatic infection ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 19}, {\"segment_text\": \"even in carefully collected lower samples .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 20}, {\"segment_text\": \"This may have important implications on the interpretation of the results on the diagnostic setting .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 21}]}"}]}
{"paper_id": "75a14c9f86596159e4e716f48ee49137bd558e0d", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nPorcine epidemic diarrhea virus ( PEDV ) is an emerging pathogenic coronavirus that causes a significant economic burden to the swine industry . The virus infects the intestinal epithelium and causes villous atrophy , resulting in diarrhea and dehydration . Interaction of the viral spike ( S ) surface glycoprotein − through its S1 subunit − with the host cell receptor is the first step in infection and the main determinant for virus tropism . As for several other alphacoronaviruses including the porcine transmissible gastroenteritis virus ( TGEV ) and the human coronavirus 229E ( HCoV-229E ) , the aminopeptidase N ( APN ) protein was reported to be a functional receptor for PEDV . In this study we examined the role of APN as a receptor . We show that overexpression of porcine APN renders MDCK cells susceptible to TGEV , but not to PEDV . Consistently , unlike TGEV-S1 , PEDV-S1 exhibited no binding to cell-surface expressed APN or to a soluble version of APN . Moreover , preincubation of these viruses with soluble APN or pretreatment of APN expressing ST cells with soluble TGEV-S1 blocked TGEV infection , but had no effect on infection by PEDV . The combined observations indicated that APN is not required for PEDV infection . To definitively prove this conclusion , we applied CRISPR/Cas9 genome engineering to knock out APN expression in PEDV-susceptible porcine ( ST ) and human cell lines ( Huh7 and HeLa ) . As a consequence these cells no longer bound TGEV-S1 and HCoV-229E-S1 at their surface and were resistant to infection by the corresponding viruses . However , genetic ablation of APN expression had no effect on their infectability by PEDV , demonstrating that APN is not essential for PEDV cell entry .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"Porcine epidemic diarrhea virus ( PEDV ) is an emerging pathogenic coronavirus that causes a significant economic burden to the swine industry .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 1}, {\"segment_text\": \"The virus infects the intestinal epithelium and causes villous atrophy ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 2}, {\"segment_text\": \"resulting in diarrhea and dehydration .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Interaction of the viral spike ( S ) surface glycoprotein − through its S1 subunit − with the host cell receptor is the first step in infection and the main determinant for virus tropism .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 4}, {\"segment_text\": \"As for several other alphacoronaviruses including the porcine transmissible gastroenteritis virus ( TGEV ) and the human coronavirus 229E ( HCoV-229E ) ,\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 5}, {\"segment_text\": \"the aminopeptidase N ( APN ) protein was reported to be a functional receptor for PEDV .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 6}, {\"segment_text\": \"In this study we examined the role of APN as a receptor .\", \"label\": \"purpose\", \"decision_reference\": \"purpose.rule\", \"id\": 7}, {\"segment_text\": \"We show that overexpression of porcine APN renders MDCK cells susceptible to TGEV , but not to PEDV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Consistently , unlike TGEV-S1 , PEDV-S1 exhibited no binding to cell-surface expressed APN or to a soluble version of APN .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"Moreover , preincubation of these viruses with soluble APN or pretreatment of APN expressing ST cells with soluble TGEV-S1 blocked TGEV infection ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 10}, {\"segment_text\": \"but had no effect on infection by PEDV .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 11}, {\"segment_text\": \"The combined observations indicated that APN is not required for PEDV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"To definitively prove this conclusion ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 13}, {\"segment_text\": \"we applied CRISPR/Cas9 genome engineering to knock out APN expression in PEDV-susceptible porcine ( ST ) and human cell lines ( Huh7 and HeLa ) .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 14}, {\"segment_text\": \"As a consequence these cells no longer bound TGEV-S1 and HCoV-229E-S1 at their surface and were resistant to infection by the corresponding viruses .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 15}, {\"segment_text\": \"However , genetic ablation of APN expression had no effect on their infectability by PEDV ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 16}, {\"segment_text\": \"demonstrating that APN is not essential for PEDV cell entry .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 17}]}"}]}
{"paper_id": "34f9f958f686a44e5ace7a5ec825a69298e63764", "messages": [{"role": "system", "content": "You are a precise annotator for scientific abstracts. You receive a COMPLETE abstract as running text. Your task has two steps:\n\n1. SEGMENT: Split the abstract into consecutive segments (clauses). A segment is the smallest unit that carries its own rhetorical function. A sentence may split into several segments when its function changes. The segments must cover the original text without gaps or overlaps.\n\n2. LABEL: Assign each segment exactly one of five research aspects:\n- background: known context, motivation, problem, prior state of research.\n- purpose: the concrete aim, research question, or hypothesis of THIS work.\n- method: how the work was carried out (procedure, materials, data, analysis).\n- finding: results, outcomes, conclusions, implications of THIS work.\n- other: anything with no research function (boilerplate, copyright, metadata, broken fragments).\n\nClassify by the rhetorical FUNCTION of the segment, not by its subject matter.\n\nOutput: Return ONLY a JSON object with the key 'segments', an ordered list. Each segment is an object with the fields in EXACTLY this order:\n- 'segment_text': the verbatim text span of this segment,\n- 'label': one of [background, purpose, method, finding, other],\n- 'decision_reference': the verbatim codebook passage (an aspect's rule/definition or a boundary_rule) that justifies the label; reference the codebook, do NOT quote the abstract.\n- 'id': running number starting at 1 (int).\n\nNO other fields, NO text outside the JSON. The order of segments must match their order in the abstract."}, {"role": "user", "content": "ABSTRACT:\nA B S T R A C T p53 is a tumor suppressor gene that can be activated in many contexts , such as DNA damage or stressful conditions . p53 has also been shown to be important for responses to certain viral infections . Porcine epidemic diarrhea virus ( PEDV ) is a major enteric pathogen of the coronavirus family that causes extensive mortality among piglets . The involvement of p53 during PEDV infection has not previously been investigated . In this study , we detected p53 upregulation in response to PEDV infection . Treatment with a p53 specific activator or p53 overexpression markedly decreased viral replication , and we showed that there was more viral progeny produced in p53 knock-out cells than in p53 wild-type cells . Finally , we demonstrated that inhibition of viral infection by p53 was mediated via p53-dependent IFN signaling , leading to IFN-stimulated response element ( ISRE ) activation , as well as the upregulation of IFN-stimulated genes ( ISGs ) and IFN-β released from infected cells . These findings demonstrate that p53 suppresses PEDV infection , offering a novel therapeutic strategy for combatting this deadly disease in piglets . as a central regulator of the innate immune response ( Rivas et al. , https://doi .\n\nBOUNDARY RULES (apply when two aspects are close):\n{\n  \"boundary_rules\": {\n    \"background_vs_purpose\": \"background = what the world already knows / why the problem matters. purpose = what THIS study concretely intends. For 'understanding X is critical to ...' decide whether it is general motivation (background) or an explicit aim statement (purpose).\",\n    \"purpose_vs_finding\": \"purpose usually comes early and is intent ('we aim to'). finding usually comes late and is a result ('we found'). Future/infinitive -> purpose; past tense/result -> finding.\",\n    \"method_vs_finding\": \"method = the procedure (what was done). finding = the result (what came out). KEY TRAP: a clause that names an assay/analysis/instrument but states what it SHOWED is finding, not method. 'results indicated...', 'IHC showed...', 'X was generated for four strains' -> finding. 'X was measured using Y' (no result) -> method.\",\n    \"background_vs_finding\": \"background = established prior knowledge or a general mechanism that holds regardless of this study. finding = a new result/observation of THIS work. A clause describing how something generally works (e.g. 'BCRs are assembled by recombination', 'nanoparticles target locations by...') is background, even if technical -> background.\",\n    \"method_vs_purpose\": \"method = an action already carried out ('samples were examined for X', 'a consensus conference was sponsored'). purpose = a stated intention/aim ('to define the action steps', 'we aimed to'). Past-tense action -> method; infinitive of intent / aim statement -> purpose.\",\n    \"finding_vs_other\": \"finding = any substantive result, conclusion, or implication of the work, INCLUDING future applications and limitations ('the model could be used for other diseases', 'discrepancies occurred when...'). other = ONLY non-research text (copyright, metadata, URLs, garbled fragments). When a clause carries real scientific content, it is finding (or its true aspect), never other.\"\n  }\n}\n\nReturn the JSON object now."}, {"role": "assistant", "content": "{\"segments\": [{\"segment_text\": \"A B S T R A C T p53 is a tumor suppressor gene that can be activated in many contexts ,\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 1}, {\"segment_text\": \"such as DNA damage or stressful conditions .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 2}, {\"segment_text\": \"p53 has also been shown to be important for responses to certain viral infections .\", \"label\": \"background\", \"decision_reference\": \"background.rule\", \"id\": 3}, {\"segment_text\": \"Porcine epidemic diarrhea virus ( PEDV ) is a major enteric pathogen of the coronavirus family that causes extensive mortality among piglets .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 4}, {\"segment_text\": \"The involvement of p53 during PEDV infection has not previously been investigated .\", \"label\": \"background\", \"decision_reference\": \"background.definition\", \"id\": 5}, {\"segment_text\": \"In this study , we detected p53 upregulation in response to PEDV infection .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 6}, {\"segment_text\": \"Treatment with a p53 specific activator or p53 overexpression markedly decreased viral replication ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 7}, {\"segment_text\": \"and we showed that there was more viral progeny produced in p53 knock-out cells than in p53 wild-type cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 8}, {\"segment_text\": \"Finally , we demonstrated that inhibition of viral infection by p53 was mediated via p53-dependent IFN signaling ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 9}, {\"segment_text\": \"leading to IFN-stimulated response element ( ISRE ) activation ,\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 10}, {\"segment_text\": \"as well as the upregulation of IFN-stimulated genes ( ISGs ) and IFN-β released from infected cells .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 11}, {\"segment_text\": \"These findings demonstrate that p53 suppresses PEDV infection ,\", \"label\": \"finding\", \"decision_reference\": \"finding.rule\", \"id\": 12}, {\"segment_text\": \"offering a novel therapeutic strategy for combatting this deadly disease in piglets .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 13}, {\"segment_text\": \"as a central regulator of the innate immune response ( Rivas et al. , https://doi .\", \"label\": \"finding\", \"decision_reference\": \"finding.definition\", \"id\": 14}]}"}]}